Perceiving Systems, Computer Vision

Videos

BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion (CVPR 2023)

19 June 2023

06:04 Minutes

BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion (CVPR 2023)
3D Human Pose Estimation via Intuitive Physics (CVPR 2023)

19 June 2023

06:30 Minutes

3D Human Pose Estimation via Intuitive Physics (CVPR 2023)
Reconstructing Signing Avatars From Video Using Linguistic Priors (CVPR 2023)

19 June 2023

05:55 Minutes

Reconstructing Signing Avatars From Video Using Linguistic Priors (CVPR 2023)
TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments (CVPR 2023)

7 June 2023

07:41 Minutes

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments (CVPR 2023)
TEMPEH: Instant Multi-View Head Capture through Learnable Registration (CVPR 2023)

8 May 2023

05:49 Minutes

TEMPEH: Instant Multi-View Head Capture through Learnable Registration (CVPR 2023)
Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation

27 October 2022

04:54 Minutes

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation
BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information (CVPR 2022)

21 June 2022

05:00 Minutes

BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information (CVPR 2022)
MOVER: Human-Aware Object Placement for Visual Environment Reconstruction (CVPR 2022)

20 June 2022

06:13 Minutes

MOVER: Human-Aware Object Placement for Visual Environment Reconstruction (CVPR 2022)
Meta-commerce in the Age of Avatars

19 June 2022

35:38 Minutes

Meta-commerce in the Age of Avatars
SHAPY: Accurate 3D Body Shape Regression using Semantic Attributes (CVPR 2022)

17 June 2022

05:34 Minutes

SHAPY: Accurate 3D Body Shape Regression using Semantic Attributes (CVPR 2022)
GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping (CVPR'22)

16 June 2022

06:17 Minutes

GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping (CVPR'22)
EMOCA: Emotion Driven Monocular Face Capture and Animation (CVPR 2022)

26 April 2022

09:49 Minutes

EMOCA: Emotion Driven Monocular Face Capture and Animation (CVPR 2022)
OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022)

22 April 2022

03:22 Minutes

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022)
BEV: Monocular Regression of Multiple 3D People in Depth (CVPR 2022)

17 April 2022

07:21 Minutes

BEV: Monocular Regression of Multiple 3D People in Depth (CVPR 2022)
Perceiving Systems: 2016-2021

17 February 2022

23:24 Minutes

Perceiving Systems: 2016-2021
PIXIE: Collaborative Regression of Expressive Bodies using Moderation (3DV'21)

15 December 2021

04:14 Minutes

PIXIE: Collaborative Regression of Expressive Bodies using Moderation (3DV'21)
Virtuelle Tour durch die Capture Hall im Perzeptive Systeme (Deutsch)

28 October 2021

07:05 Minutes

Virtuelle Tour durch die Capture Hall im Perzeptive Systeme (Deutsch)
Perceiving Systems' Capture Hall Virtual Tour (English)

28 October 2021

07:06 Minutes

Perceiving Systems' Capture Hall Virtual Tour (English)
ROMP: Monocular, One-stage, Regression of Multiple 3D People (ICCV 2021)

13 October 2021

05:00 Minutes

ROMP: Monocular, One-stage, Regression of Multiple 3D People (ICCV 2021)
Learning to Regress Bodies using Differentiable Semantic Rendering (ICCV 2021)

13 October 2021

05:24 Minutes

Learning to Regress Bodies using Differentiable Semantic Rendering (ICCV 2021)
PARE: Part Attention Regressor for 3D Human Body Estimation (ICCV 2021)

13 October 2021

05:01 Minutes

PARE: Part Attention Regressor for 3D Human Body Estimation (ICCV 2021)
SPEC: Seeing People in the Wild with an Estimated Camera (ICCV 2021)

13 October 2021

05:00 Minutes

SPEC: Seeing People in the Wild with an Estimated Camera (ICCV 2021)
SOMA: Solving Optical Marker-Based MoCap Automatically (ICCV'2021)

7 October 2021

06:54 Minutes

SOMA: Solving Optical Marker-Based MoCap Automatically (ICCV'2021)
DECA: Siggraph 2021 talk (full version)

9 September 2021

14:16 Minutes

DECA: Siggraph 2021 talk (full version)
SAMP: Scene-Aware Motion Prediction (ICCV 2021)

17 August 2021

07:07 Minutes

SAMP: Scene-Aware Motion Prediction (ICCV 2021)
SCALE (CVPR'21 Talk Version)

22 July 2021

05:01 Minutes

SCALE (CVPR'21 Talk Version)
Putting SMPL into Scenes

22 June 2021

27:12 Minutes

Putting SMPL into Scenes
SMPL made Simple -- Introduction

22 June 2021

21:28 Minutes

SMPL made Simple -- Introduction
Problems with SMPL and fixing them with STAR

21 June 2021

34:24 Minutes

Problems with SMPL and fixing them with STAR
VIBE: Video Inference for human Body pose and shape Estimation

21 June 2021

16:07 Minutes

VIBE: Video Inference for human Body pose and shape Estimation
SMPL: Frequently Asked Questions

21 June 2021

41:56 Minutes

SMPL: Frequently Asked Questions
Visual Imitation with SMPL

21 June 2021

34:50 Minutes

Visual Imitation with SMPL
SMPLpix: Combining SMPL and Neural Rendering

21 June 2021

20:39 Minutes

SMPLpix: Combining SMPL and Neural Rendering
SMPL at Meshcapade: Digital Humans made Easy

21 June 2021

18:39 Minutes

SMPL at Meshcapade: Digital Humans made Easy
SMPL in Human Health

21 June 2021

18:58 Minutes

SMPL in Human Health
Clothing SMPL

21 June 2021

30:14 Minutes

Clothing SMPL
SMPL in VR and AR

21 June 2021

18:18 Minutes

SMPL in VR and AR
SMPL-X Application Integrations. Using SMPL-X in Blender, Unity and Unreal

21 June 2021

37:09 Minutes

SMPL-X Application Integrations. Using SMPL-X in Blender, Unity and Unreal
Robots and SMPL: Combining ROS and Unreal using Julia

21 June 2021

05:14 Minutes

Robots and SMPL: Combining ROS and Unreal using Julia
SMPL in Maya

21 June 2021

11:24 Minutes

SMPL in Maya
SMPL from Images via Optimization

21 June 2021

19:49 Minutes

SMPL from Images via Optimization
Datasets of and for SMPL and related models

21 June 2021

20:10 Minutes

Datasets of and for SMPL and related models
Regressing SMPL from Images

21 June 2021

35:28 Minutes

Regressing SMPL from Images
TUCH: On Self-Contact and Human Pose (CVPR 2021)

19 June 2021

05:01 Minutes

TUCH: On Self-Contact and Human Pose (CVPR 2021)
AGORA human pose and shape dataset (CVPR 2021)

19 June 2021

05:12 Minutes

AGORA human pose and shape dataset (CVPR 2021)
BABEL: Bodies, Action and Behavior with English Labels (CVPR 2021)

18 June 2021

04:56 Minutes

BABEL: Bodies, Action and Behavior with English Labels (CVPR 2021)
SMPL-X Blender Add-On -- Tutorial

11 May 2021

03:03 Minutes

SMPL-X Blender Add-On -- Tutorial
SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021)

3 May 2021

04:44 Minutes

SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021)
DECA: Learning an Animatable Detailed 3D Face Model from In-the-Wild Images (SIGGRAPH 2021)

3 May 2021

04:44 Minutes

DECA: Learning an Animatable Detailed 3D Face Model from In-the-Wild Images (SIGGRAPH 2021)
POSA: Populating 3D Scenes by Learning Human-Scene Interaction (CVPR 2021)

9 April 2021

04:04 Minutes

POSA: Populating 3D Scenes by Learning Human-Scene Interaction (CVPR 2021)
SMPLpix: Neural Avatars from 3D Human Models

7 January 2021

04:55 Minutes

SMPLpix: Neural Avatars from 3D Human Models
GIF: Generative Interpretable Faces

26 November 2020

04:59 Minutes

GIF: Generative Interpretable Faces
Banana phone: GRAB dataset outtakes, ECCV2020

24 August 2020

00:14 Minutes

Banana phone: GRAB dataset outtakes, ECCV2020
GRAB: A Dataset of Whole-Body Human Grasping of Objects (short version)

24 August 2020

01:31 Minutes

GRAB: A Dataset of Whole-Body Human Grasping of Objects (short version)
GRAB: A Dataset of Whole-Body Human Grasping of Objects (ECCV 2020) -- full length version

24 August 2020

06:38 Minutes

GRAB: A Dataset of Whole-Body Human Grasping of Objects (ECCV 2020) -- full length version
STAR: Sparse Trained Articulated Human Body Regressor (ECCV2020) -- short video (60s)

24 August 2020

00:58 Minutes

STAR: Sparse Trained Articulated Human Body Regressor (ECCV2020) -- short video (60s)
Monocular Expressive Body Regression through Body-Driven Attention -- short, 60 sec version

20 August 2020

01:01 Minutes

Monocular Expressive Body Regression through Body-Driven Attention -- short, 60 sec version
Monocular Expressive Body Regression through Body-Driven Attention (ECCV 2020) -- long version

20 August 2020

06:22 Minutes

Monocular Expressive Body Regression through Body-Driven Attention (ECCV 2020) -- long version
Learning to Dress 3D People in Generative Clothing (CVPR 2020)

18 August 2020

04:05 Minutes

Learning to Dress 3D People in Generative Clothing (CVPR 2020)
Perceiving Systems talk by Matthias Niessner on Learning Non-rigid Optimization

11 July 2020

05:31 Minutes

Perceiving Systems talk by Matthias Niessner on Learning Non-rigid Optimization
From Variational to Deterministic Autoencoders

19 April 2020

04:56 Minutes

From Variational to Deterministic Autoencoders
VIBE: Extra Results (CVPR 2020)

28 February 2020

06:38 Minutes

VIBE: Extra Results (CVPR 2020)
VIBE: Video Inference for Human Body Pose and Shape Estimation (CVPR 2020)

28 February 2020

05:54 Minutes

VIBE: Video Inference for Human Body Pose and Shape Estimation (CVPR 2020)
PROX dataset: 3D people interacting with 3D scenes (ICCV 2019)

27 October 2019

05:39 Minutes

PROX dataset: 3D people interacting with 3D scenes (ICCV 2019)
Attacking Optical Flow (ICCV 2019)

23 October 2019

01:51 Minutes

Attacking Optical Flow (ICCV 2019)
AMASS Dataset of 3D Human Motions

13 September 2019

03:22 Minutes

AMASS Dataset of 3D Human Motions
RingNet: Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

14 June 2019

05:48 Minutes

RingNet: 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

10 June 2019

05:27 Minutes

Expressive body capture: 3D hands, face, and body from a single image
VOCA: Capture, Learning, and Synthesis of 3D Speaking Styles

8 May 2019

04:53 Minutes

VOCA: Capture, Learning, and Synthesis of 3D Speaking Styles
Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences

18 October 2018

04:50 Minutes

Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences
SMIL: Learning an Infant Body Model from RGB-D Data

20 September 2018

01:36 Minutes

SMIL: Learning an Infant Body Model from RGB-D Data
Learning Human Optical Flow (BMVC 2018)

22 July 2018

02:35 Minutes

Learning Human Optical Flow (BMVC 2018)
Embodied Hands (SIGGRAPH Asia 2017)

12 September 2017

04:40 Minutes

Embodied Hands (SIGGRAPH Asia 2017)
FLAME: Learned face model from 4D scans (SIGGRAPH Asia, 2017)

12 September 2017

06:01 Minutes

FLAME: Learned face model from 4D scans (SIGGRAPH Asia, 2017)
Estimating body shape under clothing (CVPR 2017)

21 July 2017

06:53 Minutes

Estimating body shape under clothing (CVPR 2017)
ClothCap (SIGGRAPH 2017)

21 July 2017

05:41 Minutes

ClothCap (SIGGRAPH 2017)
MR-Flow (CVPR 2017)

16 July 2017

03:24 Minutes

MR-Flow (CVPR 2017)
3D Menagerie (CVPR'17)

16 July 2017

03:49 Minutes

3D Menagerie (CVPR'17)
Dynamic FAUST Dataset (CVPR'17)

15 July 2017

04:23 Minutes

Dynamic FAUST Dataset (CVPR'17)
Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

11 February 2017

05:50 Minutes

Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs
SMPLify: 3D Human Pose and Shape from a Single Image  (ECCV 2016)

7 October 2016

05:15 Minutes

SMPLify: 3D Human Pose and Shape from a Single Image (ECCV 2016)
SMPLify (ECCV 2016, Supplemental Material)

6 October 2016

03:16 Minutes

SMPLify (ECCV 2016, Supplemental Material)
Body Talk: Crowdshaping Realistic 3D Avatars with Words  (SIGGRAPH 2016)

26 July 2016

05:17 Minutes

Body Talk: Crowdshaping Realistic 3D Avatars with Words (SIGGRAPH 2016)
Semantic Optical Flow (CVPR 2016)

22 June 2016

03:22 Minutes

Semantic Optical Flow (CVPR 2016)
SMPL: A Skinned Multi-Person Linear Model (SIGGRAPH Asia 2015)

30 October 2015

06:28 Minutes

SMPL: A Skinned Multi-Person Linear Model (SIGGRAPH Asia 2015)
Detailed Body Shape and Pose from RGB-D Sequences (ICCV 2015)

25 October 2015

05:53 Minutes

Detailed Body Shape and Pose from RGB-D Sequences (ICCV 2015)
Intrinsic Depth (ICCV 2015)

17 October 2015

07:05 Minutes

Intrinsic Depth (ICCV 2015)
FlowCap: 2D Human Pose from Optical Flow (GCPR 2015)

1 August 2015

05:54 Minutes

FlowCap: 2D Human Pose from Optical Flow (GCPR 2015)
The Mathematics of Body Shape -- The Secret Lives of Triangles in Hollywood

18 July 2015

13:57 Minutes

The Mathematics of Body Shape -- The Secret Lives of Triangles in Hollywood
The Stitched Puppet: A Graphical Model of 3D Human Shape and Pose (CVPR 2015)

5 June 2015

04:44 Minutes

The Stitched Puppet: A Graphical Model of 3D Human Shape and Pose (CVPR 2015)
Pose-Conditioned Joint Angle Limits for 3D Human Pose Reconstruction -- CVPR 2015

2 June 2015

05:55 Minutes

Pose-Conditioned Joint Angle Limits for 3D Human Pose Reconstruction -- CVPR 2015
Dyna/4Cap -- SIGGRAPH 2015 -- Supplemental material

15 May 2015

12:01 Minutes

Dyna/4Cap -- SIGGRAPH 2015 -- Supplemental material
Dyna: A Model of Dynamic Human Shape in Motion (SIGGRAPH 2015)

15 May 2015

07:08 Minutes

Dyna: A Model of Dynamic Human Shape in Motion (SIGGRAPH 2015)
MoSh: Motion and Shape Capture from Sparse Markers (SIGGRAPH Asia 2014)

23 October 2014

05:35 Minutes

MoSh: Motion and Shape Capture from Sparse Markers (SIGGRAPH Asia 2014)
Optical Flow Estimation with Channel Constancy -- ECCV spotlight

26 August 2014

01:01 Minutes

Optical Flow Estimation with Channel Constancy -- ECCV spotlight
Modeling Blurred Video with Layers (ECCV 2014)

20 July 2014

01:59 Minutes

Modeling Blurred Video with Layers (ECCV 2014)
Intrinsic Video (ECCV 2014)

19 July 2014

05:31 Minutes

Intrinsic Video (ECCV 2014)
Scalable Robust PCA (CVPR 2014 video spotlight)

22 June 2014

00:59 Minutes

Scalable Robust PCA (CVPR 2014 video spotlight)
FAUST: Dataset and evaluation for 3D mesh registration (CVPR 2014)

9 June 2014

01:01 Minutes

FAUST: Dataset and evaluation for 3D mesh registration (CVPR 2014)
Breathing Life into Shape (SIGGRAPH 2014)

14 May 2014

06:23 Minutes

Breathing Life into Shape (SIGGRAPH 2014)
Spemannstrasse 34 Demolition

14 April 2014

00:57 Minutes

Spemannstrasse 34 Demolition
Estimating Human Pose with Flowing Puppets (ICCV 2013)

27 November 2013

07:22 Minutes

Estimating Human Pose with Flowing Puppets (ICCV 2013)
Scans to Avatars

7 November 2012

09:26 Minutes

Scans to Avatars
MPI-Sintel Optical Flow Dataset and Evaluation

10 October 2012

04:47 Minutes

MPI-Sintel Optical Flow Dataset and Evaluation
Lie Bodies: A Manifold Representation of 3D Human Shape

7 October 2012

01:40 Minutes

Lie Bodies: A Manifold Representation of 3D Human Shape
DRAPE : DRessing Any PErson (SIGGRAPH 2012)

17 May 2012

04:03 Minutes

DRAPE : DRessing Any PErson (SIGGRAPH 2012)
Tracking People Interacting with Objects

5 February 2012

00:11 Minutes

Tracking People Interacting with Objects
Predicting 3D People from 2D Pictures

5 February 2012

00:14 Minutes

Predicting 3D People from 2D Pictures
Home 3D Body Scanning using the Kinect

13 August 2011

02:06 Minutes

Home 3D Body Scanning using the Kinect
The naked truth: Estimating body shape under clothing

11 June 2010

01:13 Minutes

The naked truth: Estimating body shape under clothing
Detailed human shape and pose from images, CVPR'07

11 June 2010

00:17 Minutes

Detailed human shape and pose from images, CVPR'07
Shining a light on human pose: On shadows, shading and the estimation of pose and shape

11 June 2010

00:46 Minutes

Shining a light on human pose: On shadows, shading and the estimation of pose and shape
Recognizing facial expressions in image sequences using local parameterized models of image motion

11 June 2010

06:38 Minutes

Recognizing facial expressions in image sequences using local parameterized models of image motion
Incremental Segmentation and Tracking Over Long Image Sequences, ECCV 92

11 June 2010

03:12 Minutes

Incremental Segmentation and Tracking Over Long Image Sequences, ECCV 92
Explaining Optical Flow Events, CVPR '99

11 June 2010

00:59 Minutes

Explaining Optical Flow Events, CVPR '99
The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields

11 June 2010

04:28 Minutes

The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields
EigenTracking Robust matching and tracking of articulated objects using a view-based representation

11 June 2010

07:42 Minutes

EigenTracking Robust matching and tracking of articulated objects using a view-based representation
Probabilistic detection and tracking of motion boundaries, ICCV '99, IJCV'00

11 June 2010

00:56 Minutes

Probabilistic detection and tracking of motion boundaries, ICCV '99, IJCV'00
Robust dynamic motion estimation over time, CVPR '91

11 June 2010

03:51 Minutes

Robust dynamic motion estimation over time, CVPR '91
A framework for modeling appearance change in image sequences ICCV '98

11 June 2010

01:57 Minutes

A framework for modeling appearance change in image sequences ICCV '98
Estimating Human Shape and Pose From a Single Image

11 June 2010

01:44 Minutes

Estimating Human Shape and Pose From a Single Image