417 results
(View BibTeX file of all listed publications)
2025
OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics
Gozlan, Y., Falisse, A., Uhlrich, S., Gatti, A., Black, M., Chaudhari, A.
In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , February 2025 (inproceedings)
Pose estimation has promised to impact healthcare by enabling more practical methods to quantify nuances of human movement and biomechanics. However, despite the inherent connection between pose estimation and biomechanics, these disciplines have largely remained disparate. For example, most current pose estimation benchmarks use metrics such as Mean Per Joint Position Error, Percentage of Correct Keypoints, or mean Average Precision to assess performance, without quantifying kinematic and physiological correctness - key aspects for biomechanics. To alleviate this challenge, we develop OpenCapBench to offer an easy-to-use unified benchmark to assess common tasks in human pose estimation, evaluated under physiological constraints. OpenCapBench computes consistent kinematic metrics through joints angles provided by an open-source musculoskeletal modeling software (OpenSim). Through OpenCapBench, we demonstrate that current pose estimation models use keypoints that are too sparse for accurate biomechanics analysis. To mitigate this challenge, we introduce SynthPose, a new approach that enables finetuning of pre-trained 2D human pose models to predict an arbitrarily denser set of keypoints for accurate kinematic analysis through the use of synthetic data. Incorporating such finetuning on synthetic data of prior models leads to twofold reduced joint angle errors. Moreover, OpenCapBench allows users to benchmark their own developed models on our clinically relevant cohort. Overall, OpenCapBench bridges the computer vision and biomechanics communities, aiming to drive simultaneous advances in both areas.
2024
PuzzleAvatar: Assembling 3D Avatars from Personal Albums
Xiu, Y., Liu, Z., Tzionas, D., Black, M. J.
ACM Transactions on Graphics, 43(6), ACM, December 2024 (article) To be published
Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body images in controlled settings. What if a user could just upload their personal "OOTD" (Outfit Of The Day) photo collection and get a faithful avatar in return? The challenge is that such casual photo collections contain diverse poses, challenging viewpoints, cropped views, and occlusion (albeit with a consistent outfit, accessories and hairstyle). We address this novel "Album2Human" task by developing PuzzleAvatar, a novel model that generates a faithful 3D avatar (in a canonical pose) from a personal OOTD album, while bypassing the challenging estimation of body and camera pose. To this end, we fine-tune a foundational vision-language model (VLM) on such photos, encoding the appearance, identity, garments, hairstyles, and accessories of a person into (separate) learned tokens and instilling these cues into the VLM. In effect, we exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar. Importantly, we can customize avatars by simply inter-changing tokens. As a benchmark for this new task, we collect a new dataset, called PuzzleIOI, with 41 subjects in a total of nearly 1K OOTD configurations, in challenging partial photos with paired ground-truth 3D bodies. Evaluation shows that PuzzleAvatar not only has high reconstruction accuracy, outperforming TeCH and MVDreamBooth, but also a unique scalability to album photos, and strong robustness. Our code and data are publicly available for research purpose.
MotionFix: Text-Driven 3D Human Motion Editing
Athanasiou, N., Cseke, A., Diomataris, M., Wen, M. J. B., Varol, G.
In SIGGRAPH Asia 2024 Conference Proceedings, ACM, December 2024 (inproceedings) To be published
The focus of this paper is 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The challenges include the lack of training data and the design of a model that faithfully edits the source motion. In this paper, we address both these challenges. We build a methodology to semi-automatically collect a dataset of triplets in the form of (i) a source motion, (ii) a target motion, and (iii) an edit text, and create the new dataset. Having access to such data allows us to train a conditional diffusion model that takes both the source motion and the edit text as input. We further build various baselines trained only on text-motion pairs datasets and show superior performance of our model trained on triplets. We introduce new retrieval-based metrics for motion editing and establish a new benchmark on the evaluation set. Our results are encouraging, paving the way for further research on fine-grained motion generation. Code and models will be made publicly available.
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Ye, C., Qiu, L., Gu, X., Zuo, Q., Wu, Y., Dong, Z., Bo, L., Xiu, Y., Han, X.
ACM Transactions on Graphics, 43(6), ACM, December 2024 (article) To be published
This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However, previous attempts still struggle with stochastic inference, conflicting with the deterministic nature of the Image2Normal task, and costly ensembling step, which slows down the estimation process. Our method, StableNormal, mitigates the stochasticity of the diffusion process by reducing inference variance, thus producing "Stable-and-Sharp" normal estimates without any additional ensembling process. StableNormal works robustly under challenging imaging conditions, such as extreme lighting, blurring, and low quality. It is also robust against transparent and reflective surfaces, as well as cluttered scenes with numerous objects. Specifically, StableNormal employs a coarse-to-fine strategy, which starts with a one-step normal estimator (YOSO) to derive an initial normal guess, that is relatively coarse but reliable, then followed by a semantic-guided refinement process (SG-DRN) that refines the normals to recover geometric details. The effectiveness of StableNormal is demonstrated through competitive performance in standard datasets such as DIODE-indoor, iBims, ScannetV2 and NYUv2, and also in various downstream tasks, such as surface reconstruction and normal enhancement. These results evidence that StableNormal retains both the "stability" and "sharpness" for accurate normal estimation. StableNormal represents a baby attempt to repurpose diffusion priors for deterministic estimation. To democratize this, code and models have been publicly available.
Stable Video Portraits
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, October 2024 (inproceedings) Accepted
Rapid advances in the field of generative AI and text-to-image methods in particular have transformed the way we interact with and perceive computer-generated imagery today. In parallel, much progress has been made in 3D face reconstruction, using 3D Morphable Models (3DMM). In this paper, we present Stable Video Portraits, a novel hybrid 2D/3D generation method that outputs photorealistic videos of talking faces leveraging a large pre-trained text-to-image prior (2D), controlled via a 3DMM (3D). Specifically, we introduce a person-specific fine-tuning of a general 2D stable diffusion model which we lift to a video model by providing temporal 3DMM sequences as conditioning and by introducing a temporal denoising procedure. As an output, this model generates temporally smooth imagery of a person with 3DMM-based controls, i.e., a person-specific avatar. The facial appearance of this person-specific avatar can be edited and morphed to text-defined celebrities, without any test-time fine-tuning. The method is analyzed quantitatively and qualitatively, and we show that our method outperforms state-of-the-art monocular head avatar methods.
On predicting 3D bone locations inside the human body
Dakri, A., Arora, V., Challier, L., Keller, M., Black, M. J., Pujades, S.
In 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), October 2024 (inproceedings)
Knowing the precise location of the bones inside the human body is key in several medical tasks, such as patient placement inside an imaging device or surgical navigation inside a patient. Our goal is to predict the bone locations using only an external 3D body surface obser- vation. Existing approaches either validate their predictions on 2D data (X-rays) or with pseudo-ground truth computed from motion capture using biomechanical models. Thus, methods either suffer from a 3D-2D projection ambiguity or directly lack validation on clinical imaging data. In this work, we start with a dataset of segmented skin and long bones obtained from 3D full body MRI images that we refine into individual bone segmentations. To learn the skin to bones correlations, one needs to register the paired data. Few anatomical models allow to register a skeleton and the skin simultaneously. One such method, SKEL, has a skin and skeleton that is jointly rigged with the same pose parameters. How- ever, it lacks the flexibility to adjust the bone locations inside its skin. To address this, we extend SKEL into SKEL-J to allow its bones to fit the segmented bones while its skin fits the segmented skin. These precise fits allow us to train SKEL-J to more accurately infer the anatomical joint locations from the skin surface. Our qualitative and quantitative results show how our bone location predictions are more accurate than all existing approaches. To foster future research, we make available for research purposes the individual bone segmentations, the fitted SKEL-J models as well as the new inference methods.
Synthesizing Environment-Specific People in Photographs
Ostrek, M., O’Sullivan, C., Black, M., Thies, J.
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, October 2024 (inproceedings) Accepted
We present ESP, a novel method for context-aware full-body generation, that enables photo-realistic synthesis and inpainting of people wearing clothing that is semantically appropriate for the scene depicted in an input photograph. ESP is conditioned on a 2D pose and contextual cues that are extracted from the photograph of the scene and integrated into the generation process, where the clothing is modeled explicitly with human parsing masks (HPM). Generated HPMs are used as tight guiding masks for inpainting, such that no changes are made to the original background. Our models are trained on a dataset containing a set of in-the-wild photographs of people covering a wide range of different environments. The method is analyzed quantitatively and qualitatively, and we show that ESP outperforms the state-of-the-art on the task of contextual full-body generation.
HUMOS: Human Motion Model Conditioned on Body Shape
Tripathi, S., Taheri, O., Lassner, C., Black, M. J., Holden, D., Stoll, C.
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, October 2024 (inproceedings)
Generating realistic human motion is essential for many computer vision and graphics applications. The wide variety of human body shapes and sizes greatly impacts how people move. However, most existing motion models ignore these differences, relying on a standardized, average body. This leads to uniform motion across different body types, where movements don't match their physical characteristics, limiting diversity. To solve this, we introduce a new approach to develop a generative motion model based on body shape. We show that it's possible to train this model using unpaired data by applying cycle consistency, intuitive physics, and stability constraints, which capture the relationship between identity and movement. The resulting model generates diverse, physically plausible, and dynamically stable human motions that are both quantitatively and qualitatively more realistic than current state-of-the-art methods.
GraspXL: Generating Grasping Motions for Diverse Objects at Scale
Zhang, H., Christen, S., Fan, Z., Hilliges, O., Song, J.
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, September 2024 (inproceedings) Accepted
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
Fan, Z., Ohkawa, T., Yang, L., Lin, N., Zhou, Z., Zhou, S., Liang, J., Gao, Z., Zhang, X., Zhang, X., Li, F., Zheng, L., Lu, F., Zeid, K. A., Leibe, B., On, J., Baek, S., Prakash, A., Gupta, S., He, K., Sato, Y., Hilliges, O., Chang, H. J., Yao, A.
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, September 2024 (inproceedings) Accepted
AWOL: Analysis WithOut synthesis using Language
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, September 2024 (inproceedings)
Re-Thinking Inverse Graphics with Large Language Models
Kulits, P., Feng, H., Liu, W., Abrevaya, V., Black, M. J.
Transactions on Machine Learning Research, August 2024 (article)
Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. Successfully disentangling an image into its constituent elements, such as the shape, color, and material properties of the objects of the 3D scene that produced it, requires a comprehensive understanding of the environment. This complexity limits the ability of existing carefully engineered approaches to generalize across domains. Inspired by the zero-shot ability of large language models (LLMs) to generalize to novel contexts, we investigate the possibility of leveraging the broad world knowledge encoded in such models to solve inverse-graphics problems. To this end, we propose the Inverse-Graphics Large Language Model (IG-LLM), an inverse-graphics framework centered around an LLM, that autoregressively decodes a visual embedding into a structured, compositional 3D-scene representation. We incorporate a frozen pre-trained visual encoder and a continuous numeric head to enable end-to-end training. Through our investigation, we demonstrate the potential of LLMs to facilitate inverse graphics through next-token prediction, without the application of image-space supervision. Our analysis enables new possibilities for precise spatial reasoning about images that exploit the visual knowledge of LLMs. We release our code and data at https://ig-llm.is.tue.mpg.de/ to ensure the reproducibility of our investigation and to facilitate future research.
ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations
Grigorev, A., Becherini, G., Black, M., Hilliges, O., Thomaszewski, B.
In ACM SIGGRAPH 2024 Conference Papers, pages: 1-10, SIGGRAPH ’24, Association for Computing Machinery, New York, NY, USA, July 2024 (inproceedings)
Learning-based approaches to cloth simulation have started to show their potential in recent years. However, handling collisions and intersections in neural simulations remains a largely unsolved problem. In this work, we present ContourCraft, a learning-based solution for handling intersections in neural cloth simulations. Unlike conventional approaches that critically rely on intersection-free inputs, ContourCraft robustly recovers from intersections introduced through missed collisions, self-penetrating bodies, or errors in manually designed multi-layer outfits. The technical core of ContourCraft is a novel intersection contour loss that penalizes interpenetrations and encourages rapid resolution thereof. We integrate our intersection loss with a collision-avoiding repulsion objective into a neural cloth simulation method based on graph neural networks (GNNs). We demonstrate our method’s ability across a challenging set of diverse multi-layer outfits under dynamic human motions. Our extensive analysis indicates that ContourCraft significantly improves collision handling for learned simulation and produces visually compelling results.
Airship Formations for Animal Motion Capture and Behavior Analysis
(Best Paper)
Proceedings 2nd International Conference on Design and Engineering of Lighter-Than-Air systems (DELTAS2024), June 2024 (conference) Accepted
Using UAVs for wildlife observation and motion capture offers manifold advantages for studying animals in the wild, especially grazing herds in open terrain. The aerial perspective allows observation at a scale and depth that is not possible on the ground, offering new insights into group behavior. However, the very nature of wildlife field-studies puts traditional fixed wing and multi-copter systems to their limits: limited flight time, noise and safety aspects affect their efficacy, where lighter than air systems can remain on station for many hours. Nevertheless, airships are challenging from a ground handling perspective as well as from a control point of view, being voluminous and highly affected by wind. In this work, we showcase a system designed to use airship formations to track, follow, and visually record wild horses from multiple angles, including airship design, simulation, control, on board computer vision, autonomous operation and practical aspects of field experiments.
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
Liu, H., Zhu, Z., Becherini, G., Peng, Y., Su, M., Zhou, Y., Zhe, X., Iwamoto, N., Zheng, B., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. BEAT2 combines a MoShed SMPL-X body with FLAME head parameters and further refines the modeling of head, neck, and finger movements, offering a community-standardized, high-quality 3D motion captured dataset. EMAGE leverages masked body gesture priors during training to boost inference performance. It involves a Masked Audio Gesture Transformer, facilitating joint training on audio-to-gesture generation and masked gesture reconstruction to effectively encode audio and body gesture hints. Encoded body hints from masked gestures are then separately employed to generate facial and body movements. Moreover, EMAGE adaptively merges speech features from the audio's rhythm and content and utilizes four compositional VQ-VAEs to enhance the results' fidelity and diversity. Experiments demonstrate that EMAGE generates holistic gestures with state-of-the-art performance and is flexible in accepting predefined spatial-temporal gesture inputs, generating complete, audio-synchronized results. Our code and dataset are available.
HUGS: Human Gaussian Splats
Kocabas, M., Chang, R., Gabriel, J., Tuzel, O., Ranjan, A.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Recent advances in neural rendering have improved both training and rendering times by orders of magnitude. While these methods demonstrate state-of-the-art quality and speed, they are designed for photogrammetry of static scenes and do not generalize well to freely moving humans in the environment. In this work, we introduce Human Gaussian Splats (HUGS) that represents an animatable human together with the scene using 3D Gaussian Splatting (3DGS). Our method takes only a monocular video with a small number of (50-100) frames, and it automatically learns to disentangle the static scene and a fully animatable human avatar within 30 minutes. We utilize the SMPL body model to initialize the human Gaussians. To capture details that are not modeled by SMPL (e.g., cloth, hairs), we allow the 3D Gaussians to deviate from the human body model. Utilizing 3D Gaussians for animated humans brings new challenges, including the artifacts created when articulating the Gaussians. We propose to jointly optimize the linear blend skinning weights to coordinate the movements of individual Gaussians during animation. Our approach enables novel-pose synthesis of human and novel view synthesis of both the human and the scene. We achieve state-of-the-art rendering quality with a rendering speed of 60 FPS while being ∼100× faster to train over previous work.
HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
(Highlight)
Fan, Z., Parelli, M., Kadoglou, M. E., Kocabas, M., Chen, X., Black, M. J., Hilliges, O.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour. However, most existing methods for hand-object reconstruction from RGB either assume pre-scanned object templates or heavily rely on limited 3D hand-object data, restricting their ability to scale and generalize to more unconstrained interaction settings. To this end, we introduce HOLD -- the first category-agnostic method that reconstructs an articulated hand and object jointly from a monocular interaction video. We develop a compositional articulated implicit model that can reconstruct disentangled 3D hand and object from 2D images. We also further incorporate hand-object constraints to improve hand-object poses and consequently the reconstruction quality. Our method does not rely on 3D hand-object annotations while outperforming fully-supervised baselines in both in-the-lab and challenging in-the-wild settings. Moreover, we qualitatively show its robustness in reconstructing from in-the-wild videos.
SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes
Sanyal, S., Ghosh, P., Yang, J., Black, M. J., Thies, J., Bolkart, T.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 2362-2371, June 2024 (inproceedings)
We present SCULPT, a novel 3D generative model for clothed and textured 3D meshes of humans. Specifically, we devise a deep neural network that learns to represent the geometry and appearance distribution of clothed human bodies. Training such a model is challenging, as datasets of textured 3D meshes for humans are limited in size and accessibility. Our key observation is that there exist medium-sized 3D scan datasets like CAPE, as well as large-scale 2D image datasets of clothed humans and multiple appearances can be mapped to a single geometry. To effectively learn from the two data modalities, we propose an unpaired learning procedure for pose-dependent clothed and textured human meshes. Specifically, we learn a pose-dependent geometry space from 3D scan data. We represent this as per vertex displacements w.r.t. the SMPL model. Next, we train a geometry conditioned texture generator in an unsupervised way using the 2D image data. We use intermediate activations of the learned geometry model to condition our texture generator. To alleviate entanglement between pose and clothing type, and pose and clothing appearance, we condition both the texture and geometry generators with attribute labels such as clothing types for the geometry, and clothing colors for the texture generator. We automatically generated these conditioning labels for the 2D images based on the visual question answering model BLIP and CLIP. We validate our method on the SCULPT dataset, and compare to state-of-the-art 3D generative models for clothed human bodies.
WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
Shin, S., Kim, J., Halilaj, E., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global coordinates often assumes a flat ground plane and produces foot sliding. Third, the most accurate methods rely on computationally expensive optimization pipelines, limiting their use to offline applications. Finally, existing video-based methods are surprisingly less accurate than single-frame methods. We address these limitations with WHAM (World-grounded Humans with Accurate Motion), which accurately and efficiently reconstructs 3D human motion in a global coordinate system from video. WHAM learns to lift 2D keypoint sequences to 3D using motion capture data and fuses this with video features, integrating motion context and visual information. WHAM exploits camera angular velocity estimated from a SLAM method together with human motion to estimate the body's global trajectory. We combine this with a contact-aware trajectory refinement method that lets WHAM capture human motion in diverse conditions, such as climbing stairs. WHAM outperforms all existing 3D human motion recovery methods across multiple in-the-wild benchmarks. Code will be available for research purposes.
WANDR: Intention-guided Human Motion Generation
Diomataris, M., Athanasiou, N., Taheri, O., Wang, X., Hilliges, O., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness.A primary obstacle is the scarcity of training data that combines locomotion with goal reaching. To address this, we introduce WANDR, a data-driven model that takes an avatar's initial pose and a goal's 3D position and generates natural human motions that place the end effector (wrist) on the goal location. To solve this, we introduce novel \textit{intention} features that drive rich goal-oriented movement. \textit{Intention} guides the agent to the goal, and interactively adapts the generation to novel situations without needing to define sub-goals or the entire motion path. Crucially, intention allows training on datasets that have goal-oriented motions as well as those that do not. WANDR is a conditional Variational Auto-Encoder (c-VAE), which we train using the AMASS and CIRCLE datasets. We evaluate our method extensively and demonstrate its ability to generate natural and long-term motions that reach 3D goals and generalize to unseen goal locations.
Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles
Sklyarova, V., Zakharov, E., Hilliges, O., Black, M. J., Thies, J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
We present HAAR, a new strand-based generative model for 3D human hairstyles. Specifically, based on textual inputs, HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines. Current AI-based generative models take advantage of powerful 2D priors to reconstruct 3D content in the form of point clouds, meshes, or volumetric functions. However, by using the 2D priors, they are intrinsically limited to only recovering the visual parts. Highly occluded hair structures can not be reconstructed with those methods, and they only model the "outer shell", which is not ready to be used in physics-based rendering or simulation pipelines. In contrast, we propose a first text-guided generative method that uses 3D hair strands as an underlying representation. Leveraging 2D visual question-answering (VQA) systems, we automatically annotate synthetic hair models that are generated from a small set of artist-created hairstyles. This allows us to train a latent diffusion model that operates in a common hairstyle UV space. In qualitative and quantitative studies, we demonstrate the capabilities of the proposed model and compare it to existing hairstyle generation approaches.
4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations
Wang, W., Ho, H., Guo, C., Rong, B., Grigorev, A., Song, J., Zarate, J. J., Hilliges, O.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
The studies of human clothing for digital avatars have predominantly relied on synthetic datasets. While easy to collect, synthetic data often fall short in realism and fail to capture authentic clothing dynamics. Addressing this gap, we introduce 4D-DRESS, the first real-world 4D dataset advancing human clothing research with its high-quality 4D textured scans and garment meshes. 4D-DRESS captures 64 outfits in 520 human motion sequences amounting to a total of 78k textured scans. Creating a real-world clothing dataset is challenging, particularly in annotating and segmenting the extensive and complex 4D human scans. To address this, we develop a semi-automatic 4D human parsing pipeline. We efficiently combine a human-in-the-loop process with automation to accurately label 4D scans in diverse garments and body movements. Leveraging precise annotations and high-quality garment meshes, we establish a number of benchmarks for clothing simulation and reconstruction. 4D-DRESS offers realistic and challenging data that complements synthetic sources, paving the way for advancements in research of lifelike human clothing.
HIT: Estimating Internal Human Implicit Tissues from the Body Surface
Keller, M., Arora, V., Dakri, A., Chandhok, S., Machann, J., Fritsche, A., Black, M. J., Pujades, S.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 3480-3490, June 2024 (inproceedings)
The creation of personalized anatomical digital twins is important in the fields of medicine, computer graphics, sports science, and biomechanics. To observe a subject's anatomy, expensive medical devices (MRI or CT) are required and the creation of the digital model is often time-consuming and involves manual effort. Instead, we leverage the fact that the shape of the body surface is correlated with the internal anatomy; for example, from surface observations alone, one can predict body composition and skeletal structure. In this work, we go further and learn to infer the 3D location of three important anatomic tissues: subcutaneous adipose tissue (fat), lean tissue (muscles and organs), and long bones. To learn to infer these tissues, we tackle several key challenges. We first create a dataset of human tissues by segmenting full-body MRI scans and registering the SMPL body mesh to the body surface. With this dataset, we train HIT (Human Implicit Tissues), an implicit function that, given a point inside a body, predicts its tissue class. HIT leverages the SMPL body model shape and pose parameters to canonicalize the medical data. Unlike SMPL, which is trained from upright 3D scans, the MRI scans are taken of subjects lying on a table, resulting in significant soft-tissue deformation. Consequently, HIT uses a learned volumetric deformation field that undoes these deformations. Since HIT is parameterized by SMPL, we can repose bodies or change the shape of subjects and the internal structures deform appropriately. We perform extensive experiments to validate HIT's ability to predict plausible internal structure for novel subjects. The dataset and HIT model are publicly available to foster future research in this direction.
ChatPose: Chatting about 3D Human Pose
Feng, Y., Lin, J., Dwivedi, S. K., Sun, Y., Patel, P., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description, a process that intertwines image interpretation, world knowledge, and an understanding of body language. Traditional human pose estimation and generation methods often operate in isolation, lacking semantic understanding and reasoning abilities. ChatPose addresses these limitations by embedding SMPL poses as distinct signal tokens within a multimodal LLM, enabling the direct generation of 3D body poses from both textual and visual inputs. Leveraging the powerful capabilities of multimodal LLMs, ChatPose unifies classical 3D human pose and generation tasks while offering user interactions. Additionally, ChatPose empowers LLMs to apply their extensive world knowledge in reasoning about human poses, leading to two advanced tasks: speculative pose generation and reasoning about pose estimation. These tasks involve reasoning about humans to generate 3D poses from subtle text queries, possibly accompanied by images. We establish benchmarks for these tasks, moving beyond traditional 3D pose generation and estimation methods. Our results show that ChatPose outperforms existing multimodal LLMs and task-specific methods on these newly proposed tasks. Furthermore, ChatPose's ability to understand and generate 3D human poses based on complex reasoning opens new directions in human pose analysis.
Generative Proxemics: A Prior for 3D Social Interaction from Images
Müller, L., Ye, V., Pavlakos, G., Black, M., Kanazawa, A.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Social interaction is a fundamental aspect of human behavior and communication. The way individuals position themselves in relation to others, also known as proxemics, conveys social cues and affects the dynamics of social interaction. Reconstructing such interaction from images presents challenges because of mutual occlusion and the limited availability of large training datasets. To address this, we present a novel approach that learns a prior over the 3D proxemics two people in close social interaction and demonstrate its use for single-view 3D reconstruction. We start by creating 3D training data of interacting people using image datasets with contact annotations. We then model the proxemics using a novel denoising diffusion model called BUDDI that learns the joint distribution over the poses of two people in close social interaction. Sampling from our generative proxemics model produces realistic 3D human interactions, which we validate through a perceptual study. We use BUDDI in reconstructing two people in close proximity from a single image without any contact annotation via an optimization approach that uses the diffusion model as a prior. Our approach recovers accurate and plausible 3D social interactions from noisy initial estimates, outperforming state-of-the-art methods. Our code, data, and model are available at our project website.
VAREN: Very Accurate and Realistic Equine Network
Zuffi, S., Mellbin, Y., Li, C., Hoeschle, M., Kjellstrom, H., Polikovsky, S., Hernlund, E., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Data-driven three-dimensional parametric shape models
of the human body have gained enormous popularity
both for the analysis of visual data and for the generation
of synthetic humans. Following a similar approach
for animals does not scale to the multitude of existing animal
species, not to mention the difficulty of accessing subjects
to scan in 3D. However, we argue that for domestic
species of great importance, like the horse, it is a highly
valuable investment to put effort into gathering a large
dataset of real 3D scans, and learn a realistic 3D articulated
shape model. We introduce VAREN, a novel 3D articulated
parametric shape model learned from 3D scans
of many real horses. VAREN bridges synthesis and analysis
tasks, as the generated model instances have unprecedented
realism, while being able to represent horses of different
sizes and shapes. Differently from previous body models,
VAREN has two resolutions, an anatomical skeleton, and
interpretable, learned pose-dependent deformations, which
are related to the body muscles. We show with experiments
that this formulation has superior performance with respect
to previous strategies for modeling pose-dependent deformations
in the human body case, while also being more
compact and allowing an analysis of the relationship between
articulation and muscle deformation during articulated
motion.
MonoHair: High-Fidelity Hair Modeling from a Monocular Video
(Oral)
Wu, K., Yang, L., Kuang, Z., Feng, Y., Han, X., Shen, Y., Fu, H., Zhou, K., Zheng, Y.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Undoubtedly, high-fidelity 3D hair is crucial for achieving realism, artistic expression, and immersion in computer graphics. While existing 3D hair modeling methods have achieved impressive performance, the challenge of achieving high-quality hair reconstruction persists: they either require strict capture conditions, making practical applications difficult, or heavily rely on learned prior data, obscuring fine-grained details in images. To address these challenges, we propose a generic framework to achieve high-fidelity hair reconstruction from a monocular video, without specific requirements for environments. Our approach bifurcates the hair modeling process into two main stages: precise exterior reconstruction and interior structure inference. The exterior is meticulously crafted using our Patch-based Multi-View Optimization (PMVO). This method strategically collects and integrates hair information from multiple views, independent of prior data, to produce a high-fidelity exterior 3D line map. This map not only captures intricate details but also facilitates the inference of the hair’s inner structure. For the interior, we employ a data-driven, multi-view 3D hair reconstruction method. This method utilizes 2D structural renderings derived from the reconstructed exterior, mirroring the synthetic 2D inputs used during training. This alignment effectively bridges the domain gap between our training data and real-world data, thereby enhancing the accuracy and reliability of our interior structure inference. Lastly, we generate a strand model and resolve the directional ambiguity by our hair growth algorithm. Our experiments demonstrate that our method exhibits robustness across diverse hairstyles and achieves state-of-the-art performance.
AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion
Chhatre, K., Daněček, R., Athanasiou, N., Becherini, G., Peters, C., Black, M. J., Bolkart, T.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages: 1942-1953, June 2024 (inproceedings)
Existing methods for synthesizing 3D human gestures from speech have shown promising results, but they do not explicitly model the impact of emotions on the generated gestures. Instead, these methods directly output animations from speech without control over the expressed emotion. To address this limitation, we present AMUSE, an emotional speech-driven body animation model based on latent diffusion. Our observation is that content (i.e., gestures related to speech rhythm and word utterances), emotion, and personal style are separable. To account for this, AMUSE maps the driving audio to three disentangled latent vectors: one for content, one for emotion, and one for personal style. A latent diffusion model, trained to generate gesture motion sequences, is then conditioned on these latent vectors. Once trained, AMUSE synthesizes 3D human gestures directly from speech with control over the expressed emotions and style by combining the content from the driving speech with the emotion and style of another speech sequence. Randomly sampling the noise of the diffusion model further generates variations of the gesture with the same emotional expressivity. Qualitative, quantitative, and perceptual evaluations demonstrate that AMUSE outputs realistic gesture sequences. Compared to the state of the art, the generated gestures are better synchronized with the speech content and better represent the emotion expressed by the input speech.
Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation
Petrovich, M., Litany, O., Iqbal, U., Black, M. J., Varol, G., Peng, X. B., Rempe, D.
In CVPR Workshop on Human Motion Generation, Seattle, June 2024 (inproceedings)
Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.
A Unified Approach for Text- and Image-guided 4D Scene Generation
Zheng, Y., Li, X., Nagano, K., Liu, S., Hilliges, O., Mello, S. D.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion guidance remains largely unexplored. We propose Dream-in-4D, which features a novel two-stage approach for text-to-4D synthesis, leveraging (1) 3D and 2D diffusion guidance to effectively learn a high-quality static 3D asset in the first stage; (2) a deformable neural radiance field that explicitly disentangles the learned static asset from its deformation, preserving quality during motion learning; and (3) a multi-resolution feature grid for the deformation field with a displacement total variation loss to effectively learn motion with video diffusion guidance in the second stage. Through a user preference study, we demonstrate that our approach significantly advances image and motion quality, 3D consistency and text fidelity for text-to-4D generation compared to baseline approaches. Thanks to its motion-disentangled representation, Dream-in-4D can also be easily adapted for controllable generation where appearance is defined by one or multiple images, without the need to modify the motion learning stage. Thus, our method offers, for the first time, a unified approach for text-to-4D, image-to-4D and personalized 4D generation tasks.
Neuropostors: Neural Geometry-aware 3D Crowd Character Impostors
Ostrek, M., Mitra, N. J., O’Sullivan, C.
In 2024 27th International Conference on Pattern Recognition (ICPR), Springer, June 2024 (inproceedings) Accepted
Crowd rendering and animation was a very active research area over a decade ago, but in recent years this has lessened, mainly due to improvements in graphics acceleration hardware. Nevertheless, there is still a high demand for generating varied crowd appearances and animation for games, movie production, and mixed-reality applications. Current approaches are still limited in terms of both the behavioral and appearance aspects of virtual characters due to (i) high memory and computational demands; and (ii) person-hours needed of skilled artists in the context of short production cycles. A promising previous approach to generating varied crowds was the use of pre-computed impostor representations for crowd characters, which could replace an animation of a 3D mesh with a simplified 2D impostor for every frame of an animation sequence, e.g., Geopostors [1]. However, with their high memory demands at a time when improvements in consumer graphics accelerators were outpacing memory availability, the practicality of such methods was limited. Inspired by this early work and recent advances in the field of Neural Rendering, we present a new character representation: Neuropostors. We train a Convolutional Neural Network as a means of compressing both the geometric properties and animation key-frames for a 3D character, thereby allowing for constant-time rendering of animated characters from arbitrary camera views. Our method also allows for explicit illumination and material control, by utilizing a flexible rendering equation that is connected to the outputs of the neural network.
Real-time Monocular Full-body Capture in World Space via Sequential Proxy-to-Motion Learning
Zhang, H., Zhang, Y., Hu, L., Zhang, J., Yi, H., Zhang, S., Liu, Y.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However, due to the challenges in data collection and network designs, it remains challenging for existing solutions to achieve real-time full-body capture while being accurate in world space. In this work, we introduce ProxyCap, a human-centric proxy-to-motion learning scheme to learn world-space motions from a proxy dataset of 2D skeleton sequences and 3D rotational motions. Such proxy data enables us to build a learning-based network with accurate world-space supervision while also mitigating the generalization issues. For more accurate and physically plausible predictions in world space, our network is designed to learn human motions from a human-centric perspective, which enables the understanding of the same motion captured with different camera trajectories. Moreover, a contact-aware neural motion descent module is proposed in our network so that it can be aware of foot-ground contact and motion misalignment with the proxy observations. With the proposed learning-based solution, we demonstrate the first real-time monocular full-body capture system with plausible foot-ground contact in world space even using hand-held moving cameras.
SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis
Retsinas, G., Filntisis, P. P., Danecek, R., Abrevaya, V. F., Roussos, A., Bolkart, T., Maragos, P.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), June 2024 (inproceedings)
While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these methods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expressive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geometry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between rendering and input image further hinders the learning process. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image. As the neural rendering gets color information from sampled image pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further, it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for diverse expressions. Our qualitative, quantitative and particularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction.
Ghost on the Shell: An Expressive Representation of General 3D Shapes
Liu, Z., Feng, Y., Xiu, Y., Liu, W., Paull, L., Black, M. J., Schölkopf, B.
In Proceedings of the Twelfth International Conference on Learning Representations, May 2024 (inproceedings)
The creation of photorealistic virtual worlds requires the accurate modeling of 3D surface geometry for a wide range of objects. For this, meshes are appealing since they 1) enable fast physics-based rendering with realistic material and lighting, 2) support physical simulation, and 3) are memory-efficient for modern graphics pipelines. Recent work on reconstructing and statistically modeling 3D shape, however, has critiqued meshes as being topologically inflexible. To capture a wide range of object shapes, any 3D representation must be able to model solid, watertight, shapes as well as thin, open, surfaces. Recent work has focused on the former, and methods for reconstructing open surfaces do not support fast reconstruction with material and lighting or unconditional generative modelling. Inspired by the observation that open surfaces can be seen as islands floating on watertight surfaces, we parameterize open surfaces by defining a manifold signed distance field on watertight templates. With this parameterization, we further develop a grid-based and differentiable representation that parameterizes both watertight and non-watertight meshes of arbitrary topology. Our new representation, called Ghost-on-the-Shell (G-Shell), enables two important applications: differentiable rasterization-based reconstruction from multiview images and generative modelling of non-watertight meshes. We empirically demonstrate that G-Shell achieves state-of-the-art performance on non-watertight mesh reconstruction and generation tasks, while also performing effectively for watertight meshes.
Exploring Weight Bias and Negative Self-Evaluation in Patients with Mood Disorders: Insights from the BodyTalk Project,
Meneguzzo, P., Behrens, S. C., Pavan, C., Toffanin, T., Quiros-Ramirez, M. A., Black, M. J., Giel, K., Tenconi, E., Favaro, A.
Frontiers in Psychiatry, 15, Sec. Psychopathology, May 2024 (article)
Background: Negative body image and adverse body self-evaluation represent key psychological constructs within the realm of weight bias (WB), potentially intertwined with the negative self-evaluation characteristic of depressive symptomatology. Although WB encapsulates an implicit form of self-critical assessment, its exploration among people with mood disorders (MD) has been under-investigated. Our primary goal is to comprehensively assess both explicit and implicit WB, seeking to reveal specific dimensions that could interconnect with the symptoms of MDs.
Methods: A cohort comprising 25 MD patients and 35 demographically matched healthy peers (with 83% female representation) participated in a series of tasks designed to evaluate the congruence between various computer-generated body representations and a spectrum of descriptive adjectives. Our analysis delved into multiple facets of body image evaluation, scrutinizing the associations between different body sizes and emotionally charged adjectives (e.g., active, apple-shaped, attractive).
Results: No discernible differences emerged concerning body dissatisfaction or the correspondence of different body sizes with varying adjectives. Interestingly, MD patients exhibited a markedly higher tendency to overestimate their body weight (p = 0.011). Explicit WB did not show significant variance between the two groups, but MD participants demonstrated a notable implicit WB within a specific weight rating task for BMI between 18.5 and 25 kg/m2 (p = 0.012).
Conclusions: Despite the striking similarities in the assessment of participants’ body weight, our investigation revealed an implicit WB among individuals grappling with MD. This bias potentially assumes a role in fostering self-directed negative evaluations, shedding light on a previously unexplored facet of the interplay between WB and mood disorders.
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Liu, W., Qiu, Z., Feng, Y., Xiu, Y., Xue, Y., Yu, L., Feng, H., Liu, Z., Heo, J., Peng, S., Wen, Y., Black, M. J., Weller, A., Schölkopf, B.
In Proceedings of the Twelfth International Conference on Learning Representations (ICLR), May 2024 (inproceedings)
Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a few key desiderata that enable better parameter-efficiency. Inspired by how the Cooley-Tukey fast Fourier transform algorithm enables efficient information transmission, we propose an efficient orthogonal parameterization using butterfly structures. We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT). By subsuming OFT as a special case, BOFT introduces a generalized orthogonal finetuning framework. Finally, we conduct an extensive empirical study of adapting large vision transformers, large language models, and text-to-image diffusion models to various downstream tasks in vision and language.
The Poses for Equine Research Dataset (PFERD)
Li, C., Mellbin, Y., Krogager, J., Polikovsky, S., Holmberg, M., Ghorbani, N., Black, M. J., Kjellström, H., Zuffi, S., Hernlund, E.
Nature Scientific Data, 11, May 2024 (article)
Studies of quadruped animal motion help us to identify diseases, understand behavior and unravel the mechanics behind gaits in animals. The horse is likely the best-studied animal in this aspect, but data capture is challenging and time-consuming. Computer vision techniques improve animal motion extraction, but the development relies on reference datasets, which are scarce, not open-access and often provide data from only a few anatomical landmarks. Addressing this data gap, we introduce PFERD, a video and 3D marker motion dataset from horses using a full-body set-up of densely placed over 100 skin-attached markers and synchronized videos from ten camera angles. Five horses of diverse conformations provide data for various motions from basic poses (eg. walking, trotting) to advanced motions (eg. rearing, kicking). We further express the 3D motions with current techniques and a 3D parameterized model, the hSMAL model, establishing a baseline for 3D horse markerless motion capture. PFERD enables advanced biomechanical studies and provides a resource of ground truth data for the methodological development of markerless motion capture.
TADA! Text to Animatable Digital Avatars
Liao, T., Yi, H., Xiu, Y., Tang, J., Huang, Y., Thies, J., Black, M. J.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings) Accepted
We introduce TADA, a simple-yet-effective approach that takes textual descriptions and produces expressive 3D avatars with high-quality geometry and lifelike textures, that can be animated and rendered with traditional graphics pipelines. Existing text-based character generation methods are limited in terms of geometry and texture quality, and cannot be realistically animated due to inconsistent align-007 ment between the geometry and the texture, particularly in the face region. To overcome these limitations, TADA leverages the synergy of a 2D diffusion model and an animatable parametric body model. Specifically, we derive an optimizable high-resolution body model from SMPL-X with 3D displacements and a texture map, and use hierarchical rendering with score distillation sampling (SDS) to create high-quality, detailed, holistic 3D avatars from text. To ensure alignment between the geometry and texture, we render normals and RGB images of the generated character and exploit their latent embeddings in the SDS training process. We further introduce various expression parameters to deform the generated character during training, ensuring that the semantics of our generated character remain consistent with the original SMPL-X model, resulting in an animatable character. Comprehensive evaluations demonstrate that TADA significantly surpasses existing approaches on both qualitative and quantitative measures. TADA enables creation of large-scale digital character assets that are ready for animation and rendering, while also being easily editable through natural language. The code will be public for research purposes.
POCO: 3D Pose and Shape Estimation using Confidence
Dwivedi, S. K., Schmid, C., Yi, H., Black, M. J., Tzionas, D.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings)
The regression of 3D Human Pose and Shape HPS from an image is becoming increasingly accurate. This makes the results useful for downstream tasks like human action recognition or 3D graphics. Yet, no regressor is perfect, and accuracy can be affected by ambiguous image evidence or by poses and appearance that are unseen during training. Most current HPS regressors, however, do not report the confidence of their outputs, meaning that downstream tasks cannot differentiate accurate estimates from inaccurate ones. To address this, we develop POCO, a novel framework for training HPS regressors to estimate not only a 3D human body, but also their confidence, in a single feed-forward pass. Specifically, POCO estimates both the 3D body pose and a per-sample variance. The key idea is to introduce a Dual Conditioning Strategy (DCS) for regressing uncertainty that is highly correlated to pose reconstruction quality. The POCO framework can be applied to any HPS regressor and here we evaluate it by modifying HMR, PARE, and CLIFF. In all cases, training the network to reason about uncertainty helps it learn to more accurately estimate 3D pose. While this was not our goal, the improvement is modest but consistent. Our main motivation is to provide uncertainty estimates for downstream tasks; we demonstrate this in two ways: (1) We use the confidence estimates to bootstrap HPS training. Given unlabelled image data, we take the confident estimates of a POCO-trained regressor as pseudo ground truth. Retraining with this automatically-curated data improves accuracy. (2) We exploit uncertainty in video pose estimation by automatically identifying uncertain frames (e.g. due to occlusion) and inpainting these from confident frames.
PACE: Human and Camera Motion Estimation from in-the-wild Videos
Kocabas, M., Yuan, Y., Molchanov, P., Guo, Y., Black, M. J., Hilliges, O., Kautz, J., Iqbal, U.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings)
We present a method to estimate human motion in a global scene from moving cameras. This is a highly challenging task due to the coupling of human and camera motions in the video. To address this problem, we propose a joint optimization framework that disentangles human and camera motions using both foreground human motion priors and background scene features. Unlike existing methods that use SLAM as initialization, we propose to tightly integrate SLAM and human motion priors in an optimization that is inspired by bundle adjustment. Specifically, we optimize human and camera motions to match both the observed human pose and scene features. This design combines the strengths of SLAM and motion priors, which leads to significant improvements in human and camera motion estimation. We additionally introduce a motion prior that is suitable for batch optimization, making our approach significantly more efficient than existing approaches. Finally, we propose a novel synthetic dataset that enables evaluating camera motion in addition to human motion from dynamic videos. Experiments on the synthetic and real-world RICH datasets demonstrate that our approach substantially outperforms prior art in recovering both human and camera motions.
Physically plausible full-body hand-object interaction synthesis
Braun, J., Christen, S., Kocabas, M., Aksan, E., Hilliges, O.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings)
We propose a physics-based method for synthesizing dexterous hand-object interactions in a full-body setting. While recent advancements have addressed specific facets of human-object interactions, a comprehensive physics-based approach remains a challenge. Existing methods often focus on isolated segments of the interaction process and rely on data-driven techniques that may result in artifacts. In contrast, our proposed method embraces reinforcement learning (RL) and physics simulation to mitigate the limitations of data-driven approaches. Through a hierarchical framework, we first learn skill priors for both body and hand movements in a decoupled setting. The generic skill priors learn to decode a latent skill embedding into the motion of the underlying part. A high-level policy then controls hand-object interactions in these pretrained latent spaces, guided by task objectives of grasping and 3D target trajectory following. It is trained using a novel reward function that combines an adversarial style term with a task reward, encouraging natural motions while fulfilling the task incentives. Our method successfully accomplishes the complete interaction task, from approaching an object to grasping and subsequent manipulation. We compare our approach against kinematics-based baselines and show that it leads to more physically plausible motions.
TECA: Text-Guided Generation and Editing of Compositional 3D Avatars
Zhang, H., Feng, Y., Kulits, P., Wen, Y., Thies, J., Black, M. J.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings) To be published
Our goal is to create a realistic 3D facial avatar with hair and accessories using only a text description. While this challenge has attracted significant recent interest, existing methods either lack realism, produce unrealistic shapes, or do not support editing, such as modifications to the hairstyle. We argue that existing methods are limited because they employ a monolithic modeling approach, using a single representation for the head, face, hair, and accessories. Our observation is that the hair and face, for example, have very different structural qualities that benefit from different representations. Building on this insight, we generate avatars with a compositional model, in which the head, face, and upper body are represented with traditional 3D meshes, and the hair, clothing, and accessories with neural radiance fields (NeRF). The model-based mesh representation provides a strong geometric prior for the face region, improving realism while enabling editing of the person's appearance. By using NeRFs to represent the remaining components, our method is able to model and synthesize parts with complex geometry and appearance, such as curly hair and fluffy scarves. Our novel system synthesizes these high-quality compositional avatars from text descriptions. The experimental results demonstrate that our method, Text-guided generation and Editing of Compositional Avatars (TECA), produces avatars that are more realistic than those of recent methods while being editable because of their compositional nature. For example, our TECA enables the seamless transfer of compositional features like hairstyles, scarves, and other accessories between avatars. This capability supports applications such as virtual try-on.
ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
Zhang, H., Christen, S., Fan, Z., Zheng, L., Hwangbo, J., Song, J., Hilliges, O.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings) Accepted
We present ArtiGrasp, a novel method to synthesize bi-manual hand-object interactions that include grasping and articulation. This task is challenging due to the diversity of the global wrist motions and the precise finger control that are necessary to articulate objects. ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose. Our framework unifies grasping and articulation within a single policy guided by a single hand pose reference. Moreover, to facilitate the training of the precise finger control required for articulation, we present a learning curriculum with increasing difficulty. It starts with single-hand manipulation of stationary objects and continues with multi-agent training including both hands and non-stationary objects. To evaluate our method, we introduce Dynamic Object Grasping and Articulation, a task that involves bringing an object into a target articulated pose. This task requires grasping, relocation, and articulation. We show our method's efficacy towards this task. We further demonstrate that our method can generate motions with noisy hand-object pose estimates from an off-the-shelf image-based regressor.
TeCH: Text-guided Reconstruction of Lifelike Clothed Humans
Huang, Y., Yi, H., Xiu, Y., Liao, T., Tang, J., Cai, D., Thies, J.
In International Conference on 3D Vision (3DV 2024), March 2024 (inproceedings) Accepted
Despite recent research advancements in reconstructing clothed humans from a single image, accurately restoring the "unseen regions" with high-level details remains an unsolved challenge that lacks attention. Existing methods often generate overly smooth back-side surfaces with a blurry texture. But how to effectively capture all visual attributes of an individual from a single image, which are sufficient to reconstruct unseen areas (e.g., the back view)? Motivated by the power of foundation models, TeCH reconstructs the 3D human by leveraging 1) descriptive text prompts (e.g., garments, colors, hairstyles) which are automatically generated via a garment parsing model and Visual Question Answering (VQA), 2) a personalized fine-tuned Text-to-Image diffusion model (T2I) which learns the "indescribable" appearance. To represent high-resolution 3D clothed humans at an affordable cost, we propose a hybrid 3D representation based on DMTet, which consists of an explicit body shape grid and an implicit distance field. Guided by the descriptive prompts + personalized T2I diffusion model, the geometry and texture of the 3D humans are optimized through multi-view Score Distillation Sampling (SDS) and reconstruction losses based on the original observation. TeCH produces high-fidelity 3D clothed humans with consistent & delicate texture, and detailed full-body geometry. Quantitative and qualitative experiments demonstrate that TeCH outperforms the state-of-the-art methods in terms of reconstruction accuracy and rendering quality.
Adversarial Likelihood Estimation With One-Way Flows
Ben-Dov, O., Gupta, P. S., Abrevaya, V., Black, M. J., Ghosh, P.
In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages: 3779-3788, January 2024 (inproceedings)
Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. However, it has been noted that maximizing the log-likelihood within an energy-based setting can lead to an adversarial framework where the discriminator provides unnormalized density (often called energy). We further develop this perspective, incorporate importance sampling, and show that 1) Wasserstein GAN performs a biased estimate of the partition function, and we propose instead to use an unbiased estimator; and 2) when optimizing for likelihood, one must maximize generator entropy. This is hypothesized to provide a better mode coverage. Different from previous works, we explicitly compute the density of the generated samples. This is the key enabler to designing an unbiased estimator of the partition function and computation of the generator entropy term. The generator density is obtained via a new type of flow network, called one-way flow network, that is less constrained in terms of architecture, as it does not require a tractable inverse function. Our experimental results show that our method converges faster, produces comparable sample quality to GANs with similar architecture, successfully avoids over-fitting to commonly used datasets and produces smooth low-dimensional latent representations of the training data.
InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction from Multi-view RGB-D Images
Huang, Y., Taheri, O., Black, M. J., Tzionas, D.
International Journal of Computer Vision (IJCV), 2024 (article)
Humans constantly interact with objects to accomplish tasks. To understand such interactions, computers need to reconstruct these in 3D from images of whole bodies manipulating objects, e.g., for grasping, moving and using the latter. This involves key challenges, such as occlusion between the body and objects, motion blur, depth ambiguities, and the low image resolution of hands and graspable object parts. To make the problem tractable, the community has followed a divide-and-conquer approach, focusing either only on interacting hands, ignoring the body, or on interacting bodies, ignoring the hands. However, these are only parts of the problem. On the contrary, recent work focuses on the whole problem. The GRAB dataset addresses whole-body interaction with dexterous hands but captures motion via markers and lacks video, while the BEHAVE dataset captures video of body-object interaction but lacks hand detail. We address the limitations of prior work with InterCap, a novel method that reconstructs interacting whole-bodies and objects from multi-view RGB-D data, using the parametric whole-body SMPL-X model and known object meshes. To tackle the above challenges, InterCap uses two key observations: (i) Contact between the body and object can be used to improve the pose estimation of both. (ii) Consumer-level Azure Kinect cameras let us set up a simple and flexible multi-view RGB-D system for reducing occlusions, with spatially calibrated and temporally synchronized cameras. With our InterCap method we capture the InterCap dataset, which contains 10 subjects (5 males and 5 females) interacting with 10 daily objects of various sizes and affordances, including contact with the hands or feet. To this end, we introduce a new data-driven hand motion prior, as well as explore simple ways for automatic contact detection based on 2D and 3D cues. In total, InterCap has 223 RGB-D videos, resulting in 67,357 multi-view frames, each containing 6 RGB-D images, paired with pseudo ground-truth 3D body and object meshes. Our InterCap method and dataset fill an important gap in the literature and support many research directions. Data and code are available at https://intercap.is.tue.mpg.de.
HMP: Hand Motion Priors for Pose and Shape Estimation from Video
Duran, E., Kocabas, M., Choutas, V., Fan, Z., Black, M. J.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024 (article)
Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand’s high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing methods rely on single-image inputs, videos have useful cues to address aforementioned issues. However, existing video-based 3D hand datasets are insufficient for training feedforward models to generalize to in-the-wild scenarios. On the other hand, we have access to large human motion capture datasets which also include hand motions, e.g. AMASS. Therefore, we develop a generative motion prior specific for hands, trained on the AMASS dataset which features diverse and high-quality hand motions. This motion prior is then employed for video-based 3D hand motion estimation following a latent optimization approach. Our integration of a robust motion prior significantly enhances performance, especially in occluded scenarios. It produces stable, temporally consistent results that surpass conventional single-frame methods. We demonstrate our method’s efficacy via qualitative and quantitative evaluations on the HO3D and DexYCB datasets, with special emphasis on an occlusion-focused subset of HO3D.
2023
FLARE: Fast learning of Animatable and Relightable Mesh Avatars
Bharadwaj, S., Zheng, Y., Hilliges, O., Black, M. J., Abrevaya, V. F.
ACM Transactions on Graphics, 42(6):204:1-204:15, December 2023 (article) Accepted
Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. While 3D meshes enable efficient processing and are highly portable, they lack realism in terms of shape and appearance. Neural representations, on the other hand, are realistic but lack compatibility and are slow to train and render. Our key insight is that it is possible to efficiently learn high-fidelity 3D mesh representations via differentiable rendering by exploiting highly-optimized methods from traditional computer graphics and approximating some of the components with neural networks. To that end, we introduce FLARE, a technique that enables the creation of animatable and relightable mesh avatars from a single monocular video. First, we learn a canonical geometry using a mesh representation, enabling efficient differentiable rasterization and straightforward animation via learned blendshapes and linear blend skinning weights. Second, we follow physically-based rendering and factor observed colors into intrinsic albedo, roughness, and a neural representation of the illumination, allowing the learned avatars to be relit in novel scenes. Since our input videos are captured on a single device with a narrow field of view, modeling the surrounding environment light is non-trivial. Based on the split-sum approximation for modeling specular reflections, we address this by approximating the pre-filtered environment map with a multi-layer perceptron (MLP) modulated by the surface roughness, eliminating the need to explicitly model the light. We demonstrate that our mesh-based avatar formulation, combined with learned deformation, material, and lighting MLPs, produces avatars with high-quality geometry and appearance, while also being efficient to train and render compared to existing approaches.
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
Qiu*, Z., Liu*, W., Feng, H., Xue, Y., Feng, Y., Liu, Z., Zhang, D., Weller, A., Schölkopf, B.
Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 36, pages: 79320-79362, (Editors: A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine), Curran Associates, Inc., December 2023, *equal contribution (conference)
Large text-to-image diffusion models have impressive capabilities in generating photorealistic images from text prompts. How to effectively guide or control these powerful models to perform different downstream tasks becomes an important open problem. To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks. Unlike existing methods, OFT can provably preserve hyperspherical energy which characterizes the pairwise neuron relationship on the unit hypersphere. We find that this property is crucial for preserving the semantic generation ability of text-to-image diffusion models. To improve finetuning stability, we further propose Constrained Orthogonal Finetuning (COFT) which imposes an additional radius constraint to the hypersphere.
Specifically, we consider two important finetuning text-to-image tasks: subject-driven generation where the goal is to generate subject-specific images given a few images of a subject and a text prompt, and controllable generation where the goal is to enable the model to take in additional control signals. We empirically show that our OFT framework outperforms existing methods in generation quality and convergence speed.
Emotional Speech-Driven Animation with Content-Emotion Disentanglement
Daněček, R., Chhatre, K., Tripathi, S., Wen, Y., Black, M., Bolkart, T.
In ACM, December 2023 (inproceedings) Accepted
To be widely adopted, 3D facial avatars must be animated easily, realistically, and directly from speech signals. While the best recent methods generate 3D animations that are synchronized with the input audio, they largely ignore the impact of emotions on facial expressions. Realistic facial animation requires lip-sync together with the natural expression of emotion. To that end, we propose EMOTE (Expressive Model Optimized for Talking with Emotion), which generates 3D talking-head avatars that maintain lip-sync from speech while enabling explicit control over the expression of emotion. To achieve this, we supervise EMOTE with decoupled losses for speech (i.e., lip-sync) and emotion. These losses are based on two key observations: (1) deformations of the face due to speech are spatially localized around the mouth and have high temporal frequency, whereas (2) facial expressions may deform the whole face and occur over longer intervals. Thus, we train EMOTE with a per-frame lip-reading loss to preserve the speech-dependent content, while supervising emotion at the sequence level. Furthermore, we employ a content-emotion exchange mechanism in order to supervise different emotions on the same audio, while maintaining the lip motion synchronized with the speech. To employ deep perceptual losses without getting undesirable artifacts, we devise a motion prior in the form of a temporal VAE. Due to the absence of high-quality aligned emotional 3D face datasets with speech, EMOTE is trained with 3D pseudo-ground-truth extracted from an emotional video dataset (i.e., MEAD). Extensive qualitative and perceptual evaluations demonstrate that EMOTE produces speech-driven facial animations with better lip-sync than state-of-the-art methods trained on the same data, while offering additional, high-quality emotional control.