Timo Bolkart

Research Scientist

Perceiving Systems

Office: N3.009
Max-Planck-Ring 4
72076 Tübingen
Germany

https://sites.google.com/site/bo...

My research is in the areas of computer vision, computer graphics, and machine learning. My research focus is on understanding the shape and deformations of complex 3-dimensional objects like human bodies and human faces. I am especially interested in non-rigid shape analysis, statistical modeling of various kinds of shapes, the analysis of 3D motion data, and a wide variety of topics related to 3D geometry.

For more details, including a complete list of publications (including all pre-prints), available software, and available data related to previous projects, please visit https://sites.google.com/site/bolkartt

statistical modelling shape analysis 3D vision motion analysis face body

3D Body Shape and Pose from Images

Much of the field has focused on estimating 2D joints, 3D joints, or the skeleton of the body. We focus on estimating the full 3D shape and pose. This is crucial for reasoning about interactions. Having the ability to do so from RGB images enables markerless motion capture and provides the foundation for h...

Federica Bogo Angjoo Kanazawa Christoph Lassner Peter Vincent Gehler Javier Romero Michael Black Gerard Pons-Moll Martin Kiefel Yinghao Huang Ijaz Akhter Georgios Pavlakos Vassilis Choutas Nima Ghorbani Ahmed Osman Timo Bolkart Dimitrios Tzionas Muhammed Kocabas Nikos Athanasiou

Expressive Body Models

Bodies in computer vision have often been an afterthought. Human pose is often represented by 10-12 body joints in 2D or 3D. This is inspired by Johannson's moving light displays, which showed that some human actions can be recognized from the motion of the major joints of the body. But the joint...

Michael Black Dimitrios Tzionas Timo Bolkart Ahmed Osman Vassilis Choutas Georgios Pavlakos Nima Ghorbani

Faces and Expressions

Faces, their shape, and their motion are essential to communication. Consequently, we want a model of the face that can capture the full range of face shapes and expressions. Such a model should be realistic, easy to animate, easy to fit to data, and should support inference about human emotion and speech....

Michael Black Timo Bolkart Anurag Ranjan Soubhik Sanyal Tianye Li Javier Romero Cassidy Laidlaw

Learning Deep Representations of 3D

Much of our work focuses on 3D models of objects and scenes. We would like to take advantage of current deep learning approaches in representing and reasoning about 3D. Unfortunately, the standard 2D convolutional models do not readily extend to 3D because they do not match well current 3D data structures....

Michael Black Gernot Riegler Osman Ulusoy Andreas Geiger Anurag Ranjan Timo Bolkart Soubhik Sanyal

10 results (View BibTeX file of all listed publications)

2020

GIF: Generative Interpretable Faces

Ghosh, P., Gupta, P. S., Uziel, R., Ranjan, A., Black, M. J., Bolkart, T.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract

Photo-realistic visualization and animation of expressive human faces have been a long standing challenge. 3D face modeling methods provide parametric control but generates unrealistic images, on the other hand, generative 2D models like GANs (Generative Adversarial Networks) output photo-realistic face images, but lack explicit control. Recent methods gain partial control, either by attempting to disentangle different factors in an unsupervised manner, or by adding control post hoc to a pre-trained model. Unconditional GANs, however, may entangle factors that are hard to undo later. We condition our generative model on pre-defined control parameters to encourage disentanglement in the generation process. Specifically, we condition StyleGAN2 on FLAME, a generative 3D face model. While conditioning on FLAME parameters yields unsatisfactory results, we find that conditioning on rendered FLAME geometry and photometric details works well. This gives us a generative 2D face model named GIF (Generative Interpretable Faces) that offers FLAME's parametric control. Here, interpretable refers to the semantic meaning of different parameters. Given FLAME parameters for shape, pose, expressions, parameters for appearance, lighting, and an additional style vector, GIF outputs photo-realistic face images. We perform an AMT based perceptual study to quantitatively and qualitatively evaluate how well GIF follows its conditioning. The code, data, and trained model are publicly available for research purposes at http://gif.is.tue.mpg.de

pdf project code video [BibTex]

2020

Ghosh, P., Gupta, P. S., Uziel, R., Ranjan, A., Black, M. J., Bolkart, T. GIF: Generative Interpretable Faces In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

pdf project code video [BibTex]

STAR: Sparse Trained Articulated Human Body Regressor

Osman, A. A. A., Bolkart, T., Black, M. J.

In European Conference on Computer Vision (ECCV) , LNCS 12355, pages: 598-613, August 2020 (inproceedings)

Abstract

The SMPL body model is widely used for the estimation, synthesis, and analysis of 3D human pose and shape. While popular, we show that SMPL has several limitations and introduce STAR, which is quantitatively and qualitatively superior to SMPL. First, SMPL has a huge number of parameters resulting from its use of global blend shapes. These dense pose-corrective offsets relate every vertex on the mesh to all the joints in the kinematic tree, capturing spurious long-range correlations. To address this, we define per-joint pose correctives and learn the subset of mesh vertices that are influenced by each joint movement. This sparse formulation results in more realistic deformations and significantly reduces the number of model parameters to 20% of SMPL. When trained on the same data as SMPL, STAR generalizes better despite having many fewer parameters. Second, SMPL factors pose-dependent deformations from body shape while, in reality, people with different shapes deform differently. Consequently, we learn shape-dependent pose-corrective blend shapes that depend on both body pose and BMI. Third, we show that the shape space of SMPL is not rich enough to capture the variation in the human population. We address this by training STAR with an additional 10,000 scans of male and female subjects, and show that this results in better model generalization. STAR is compact, generalizes better to new bodies and is a drop-in replacement for SMPL. STAR is publicly available for research purposes at http://star.is.tue.mpg.de.

Project Page Code Video paper supplemental DOI [BibTex]

Osman, A. A. A., Bolkart, T., Black, M. J. STAR: Sparse Trained Articulated Human Body Regressor In European Conference on Computer Vision (ECCV) , LNCS 12355, pages: 598-613, August 2020 (inproceedings)

Project Page Code Video paper supplemental DOI [BibTex]

3D Morphable Face Models - Past, Present and Future

Egger, B., Smith, W. A. P., Tewari, A., Wuhrer, S., Zollhoefer, M., Beeler, T., Bernard, F., Bolkart, T., Kortylewski, A., Romdhani, S., Theobalt, C., Blanz, V., Vetter, T.

ACM Transactions on Graphics, 39(5), August 2020 (article)

Abstract

In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications.

project page pdf preprint DOI [BibTex]

Egger, B., Smith, W. A. P., Tewari, A., Wuhrer, S., Zollhoefer, M., Beeler, T., Bernard, F., Bolkart, T., Kortylewski, A., Romdhani, S., Theobalt, C., Blanz, V., Vetter, T. 3D Morphable Face Models - Past, Present and Future ACM Transactions on Graphics, 39(5), August 2020 (article)

project page pdf preprint DOI [BibTex]

Monocular Expressive Body Regression through Body-Driven Attention

Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M. J.

In Computer Vision – ECCV 2020, LNCS 12355, pages: 20-40, Springer International Publishing, Cham, August 2020 (inproceedings)

Abstract

To understand how people look, interact, or perform tasks,we need to quickly and accurately capture their 3D body, face, and hands together from an RGB image. Most existing methods focus only on parts of the body. A few recent approaches reconstruct full expressive 3D humans from images using 3D body models that include the face and hands. These methods are optimization-based and thus slow, prone to local optima, and require 2D keypoints as input. We address these limitations by introducing ExPose (EXpressive POse and Shape rEgression), which directly regresses the body, face, and hands, in SMPL-X format, from an RGB image. This is a hard problem due to the high dimensionality of the body and the lack of expressive training data. Additionally, hands and faces are much smaller than the body, occupying very few image pixels. This makes hand and face estimation hard when body images are downscaled for neural networks. We make three main contributions. First, we account for the lack of training data by curating a dataset of SMPL-X fits on in-the-wild images. Second, we observe that body estimation localizes the face and hands reasonably well. We introduce body-driven attention for face and hand regions in the original image to extract higher-resolution crops that are fed to dedicated refinement modules. Third, these modules exploit part-specific knowledge from existing face and hand-only datasets. ExPose estimates expressive 3D humans more accurately than existing optimization methods at a small fraction of the computational cost. Our data, model and code are available for research at https://expose.is.tue.mpg.de.

code Short video Long video arxiv pdf suppl link (url) DOI Project Page Project Page [BibTex]

Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M. J. Monocular Expressive Body Regression through Body-Driven Attention In Computer Vision – ECCV 2020, LNCS 12355, pages: 20-40, Springer International Publishing, Cham, August 2020 (inproceedings)

code Short video Long video arxiv pdf suppl link (url) DOI Project Page Project Page [BibTex]

2019

Decoding the Viewpoint and Identity of Faces and Bodies

Foster, C., Zhao, M., Bolkart, T., Black, M., Bartels, A., Bülthoff, I.

Journal of Vision, 19(10): 54c, pages: 54-55, Arvo Journals, September 2019 (article)

Abstract

(2019). . , 19(10): 25.13, 54-55. doi: Zitierlink: http://hdl.handle.net/21.11116/0000-0003-7493-4

link (url) DOI [BibTex]

2019

Foster, C., Zhao, M., Bolkart, T., Black, M., Bartels, A., Bülthoff, I. Decoding the Viewpoint and Identity of Faces and Bodies Journal of Vision, 19(10): 54c, pages: 54-55, Arvo Journals, September 2019 (article)

link (url) DOI [BibTex]

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Sanyal, S., Bolkart, T., Feng, H., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 7763-7772, June 2019 (inproceedings)

Abstract

The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack ground truth 3D shape. To train a network without any 2D-to-3D supervision, we present RingNet, which learns to compute 3D face shape from a single image. Our key observation is that an individual’s face shape is constant across images, regardless of expression, pose, lighting, etc. RingNet leverages multiple images of a person and automatically detected 2D face features. It uses a novel loss that encourages the face shape to be similar when the identity is the same and different for different people. We achieve invariance to expression by representing the face using the FLAME model. Once trained, our method takes a single image and outputs the parameters of FLAME, which can be readily animated. Additionally we create a new database of faces “not quite in-the-wild” (NoW) with 3D head scans and high-resolution images of the subjects in a wide variety of conditions. We evaluate publicly available methods and find that RingNet is more accurate than methods that use 3D supervision. The dataset, model, and results are available for research purposes.

code pdf preprint link (url) Project Page [BibTex]

Sanyal, S., Bolkart, T., Feng, H., Black, M. J. Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 7763-7772, June 2019 (inproceedings)

code pdf preprint link (url) Project Page [BibTex]

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A. A., Tzionas, D., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 10975-10985, June 2019 (inproceedings)

Abstract

To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8x over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

video code pdf suppl poster link (url) DOI Project Page [BibTex]

Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A. A., Tzionas, D., Black, M. J. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 10975-10985, June 2019 (inproceedings)

video code pdf suppl poster link (url) DOI Project Page [BibTex]

Capture, Learning, and Synthesis of 3D Speaking Styles

Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 10101-10111, June 2019 (inproceedings)

Abstract

Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input—even speech in languages other than English—and realistically animates a wide range of adult faces. Conditioning on subject labels during training allows the model to learn a variety of realistic speaking styles. VOCA also provides animator controls to alter speaking style, identity-dependent facial shape, and pose (i.e. head, jaw, and eyeball rotations) during animation. To our knowledge, VOCA is the only realistic 3D facial animation model that is readily applicable to unseen subjects without retargeting. This makes VOCA suitable for tasks like in-game video, virtual reality avatars, or any scenario in which the speaker, speech, or language is not known in advance. We make the dataset and model available for research purposes at http://voca.is.tue.mpg.de.

code Project Page video paper [BibTex]

Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M. J. Capture, Learning, and Synthesis of 3D Speaking Styles In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 10101-10111, June 2019 (inproceedings)

code Project Page video paper [BibTex]

2018

Generating 3D Faces using Convolutional Mesh Autoencoders

Ranjan, A., Bolkart, T., Sanyal, S., Black, M. J.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11207, pages: 725-741, Springer, Cham, September 2018 (inproceedings)

Abstract

Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn a latent representation of a face using linear subspaces or higher-order tensor generalizations. Due to this linearity, they can not capture extreme deformations and non-linear expressions. To address this, we introduce a versatile model that learns a non-linear representation of a face using spectral convolutions on a mesh surface. We introduce mesh sampling operations that enable a hierarchical mesh representation that captures non-linear variations in shape and expression at multiple scales within the model. In a variational setting, our model samples diverse realistic 3D faces from a multivariate Gaussian distribution. Our training data consists of 20,466 meshes of extreme expressions captured over 12 different subjects. Despite limited training data, our trained model outperforms state-of-the-art face models with 50% lower reconstruction error, while using 75% fewer parameters. We also show that, replacing the expression space of an existing state-of-the-art face model with our autoencoder, achieves a lower reconstruction error. Our data, model and code are available at http://coma.is.tue.mpg.de/.

Code (tensorflow) Code (pytorch) Project Page paper supplementary DOI Project Page Project Page [BibTex]

2018

Ranjan, A., Bolkart, T., Sanyal, S., Black, M. J. Generating 3D Faces using Convolutional Mesh Autoencoders In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11207, pages: 725-741, Springer, Cham, September 2018 (inproceedings)

Code (tensorflow) Code (pytorch) Project Page paper supplementary DOI Project Page Project Page [BibTex]

2017

Learning a model of facial shape and expression from 4D scans

Li, T., Bolkart, T., Black, M. J., Li, H., Romero, J.

ACM Transactions on Graphics, 36(6):194:1-194:17, November 2017, Two first authors contributed equally (article)

Abstract

The field of 3D face modeling has a large gap between high-end and low-end methods. At the high end, the best facial animation is indistinguishable from real humans, but this comes at the cost of extensive manual labor. At the low end, face capture from consumer depth sensors relies on 3D face models that are not expressive enough to capture the variability in natural facial shape and expression. We seek a middle ground by learning a facial model from thousands of accurately aligned 3D scans. Our FLAME model (Faces Learned with an Articulated Model and Expressions) is designed to work with existing graphics software and be easy to fit to data. FLAME uses a linear shape space trained from 3800 scans of human heads. FLAME combines this linear shape space with an articulated jaw, neck, and eyeballs, pose-dependent corrective blendshapes, and additional global expression from 4D face sequences in the D3DFACS dataset along with additional 4D sequences.We accurately register a template mesh to the scan sequences and make the D3DFACS registrations available for research purposes. In total the model is trained from over 33, 000 scans. FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model. We compare FLAME to these models by fitting them to static 3D scans and 4D sequences using the same optimization method. FLAME is significantly more accurate and is available for research purposes (http://flame.is.tue.mpg.de).

data/model video code chumpy code tensorflow paper supplemental Project Page [BibTex]

2017

Li, T., Bolkart, T., Black, M. J., Li, H., Romero, J. Learning a model of facial shape and expression from 4D scans ACM Transactions on Graphics, 36(6):194:1-194:17, November 2017, Two first authors contributed equally (article)

data/model video code chumpy code tensorflow paper supplemental Project Page [BibTex]

Timo Bolkart

3D Body Shape and Pose from Images

Expressive Body Models

Faces and Expressions

Learning Deep Representations of 3D

2020

GIF: Generative Interpretable Faces

2020

STAR: Sparse Trained Articulated Human Body Regressor

3D Morphable Face Models - Past, Present and Future

Monocular Expressive Body Regression through Body-Driven Attention

2019

Decoding the Viewpoint and Identity of Faces and Bodies

2019

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Capture, Learning, and Synthesis of 3D Speaking Styles

2018

Generating 3D Faces using Convolutional Mesh Autoencoders

2018

2017

Learning a model of facial shape and expression from 4D scans

2017

Latest News

Links

Contact Us