Michael Black

@UCqNJuPO0tyV6eWfYB7lcsvw - 7.1K subscribers

The Perceiving Systems department at the MPI for Intelligent Systems combines research on computer vision, graphics, and machine learning to teach computers to see and understand humans and their behavior.

Home Videos Live Playlists

BEDLAM2.0: Synthetic Humans and Cameras in Motion (NeurIPS 2025)

BEDLAM2.0: Synthetic Humans and Cameras in Motion (NeurIPS 2025) Michael Black

2.1K views - 3 months ago

ChatHuman: Reasoning about 3D humans and their behavior

ChatHuman: Reasoning about 3D humans and their behavior Michael Black

305 views - 7 months ago

Humanoid motion generation in real-time. Learned from motion capture data.

Humanoid motion generation in real-time. Learned from motion capture data. Michael Black

423 views - 7 months ago

Realtime 3D human motion capture from video for robot control and training

Realtime 3D human motion capture from video for robot control and training Michael Black

442 views - 7 months ago

3D human motion capture from video with MoCapade3.0

3D human motion capture from video with MoCapade3.0 Michael Black

682 views - 7 months ago

SMPL-X capture and transfer to G1

SMPL-X capture and transfer to G1 Michael Black

692 views - 7 months ago

PromptHMR: Promptable Human Mesh Recovery (CVPR 2025)

PromptHMR: Promptable Human Mesh Recovery (CVPR 2025) Michael Black

1K views - 8 months ago

CameraHMR: Aligning People with Perspective (3DV 2025)

CameraHMR: Aligning People with Perspective (3DV 2025) Michael Black

1.8K views - 11 months ago

MotionFix: Text-Driven 3DHuman Motion Editing (SIGGRAPH Asia 2024)

MotionFix: Text-Driven 3DHuman Motion Editing (SIGGRAPH Asia 2024) Michael Black

1.4K views - 1 year ago

SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation (ICCV 2023)

SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation (ICCV 2023) Michael Black

712 views - 1 year ago

Cyber Valley Days 2024: A look back. A look forward. A call to action.

Cyber Valley Days 2024: A look back. A look forward. A call to action. Michael Black

857 views - 1 year ago

VAREN: Very Accurate and Realistic Equine Network (CVPR 2024, HD)

VAREN: Very Accurate and Realistic Equine Network (CVPR 2024, HD) Michael Black

990 views - 1 year ago

VAREN: Very Accurate and Realistic Equine Network (CVPR 2024)

VAREN: Very Accurate and Realistic Equine Network (CVPR 2024) Michael Black

463 views - 1 year ago

AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion (CVPR 2024)

AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion (CVPR 2024) Michael Black

1.8K views - 1 year ago

SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes

SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes Michael Black

880 views - 1 year ago

[CVPR'24 Highlight] HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects

[CVPR'24 Highlight] HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects Michael Black

1.8K views - 1 year ago

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

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

10.2K views - 2 years ago

3D Human Pose Estimation via Intuitive Physics (CVPR 2023)

3D Human Pose Estimation via Intuitive Physics (CVPR 2023) Michael Black

9K views - 2 years ago

Reconstructing Signing Avatars From Video Using Linguistic Priors (CVPR 2023)

Reconstructing Signing Avatars From Video Using Linguistic Priors (CVPR 2023) Michael Black

2.2K views - 2 years ago

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments (CVPR 2023)

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments (CVPR 2023) Michael Black

5.2K views - 2 years ago

TEMPEH: Instant Multi-View Head Capture through Learnable Registration (CVPR 2023)

TEMPEH: Instant Multi-View Head Capture through Learnable Registration (CVPR 2023) Michael Black

4.1K views - 2 years ago

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation Michael Black

1.2K views - 3 years ago

BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information (CVPR 2022)

BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information (CVPR 2022) Michael Black

3K views - 3 years ago

MOVER: Human-Aware Object Placement for Visual Environment Reconstruction (CVPR 2022)

MOVER: Human-Aware Object Placement for Visual Environment Reconstruction (CVPR 2022) Michael Black

1.2K views - 3 years ago

Meta-commerce in the Age of Avatars

Meta-commerce in the Age of Avatars Michael Black

2.2K views - 3 years ago

SHAPY: Accurate 3D Body Shape Regression using Semantic Attributes (CVPR 2022)

SHAPY: Accurate 3D Body Shape Regression using Semantic Attributes (CVPR 2022) Michael Black

6.7K views - 3 years ago

GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping (CVPR'22)

GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping (CVPR'22) Michael Black

3.7K views - 3 years ago

EMOCA: Emotion Driven Monocular Face Capture and Animation (CVPR 2022)

EMOCA: Emotion Driven Monocular Face Capture and Animation (CVPR 2022) Michael Black

6.2K views - 3 years ago

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022)

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022) Michael Black

5.9K views - 3 years ago

BEV: Monocular Regression of Multiple 3D People in Depth (CVPR 2022)

BEV: Monocular Regression of Multiple 3D People in Depth (CVPR 2022) Michael Black

6.9K views - 3 years ago

Perceiving Systems: 2016-2021

Perceiving Systems: 2016-2021 Michael Black

1.7K views - 4 years ago

PIXIE: Collaborative Regression of Expressive Bodies using Moderation (3DV'21)

PIXIE: Collaborative Regression of Expressive Bodies using Moderation (3DV'21) Michael Black

3.8K views - 4 years ago

Virtuelle Tour durch die Capture Hall im Perzeptive Systeme (Deutsch)

Virtuelle Tour durch die Capture Hall im Perzeptive Systeme (Deutsch) Michael Black

770 views - 4 years ago

Perceiving Systems' Capture Hall Virtual Tour (English)

Perceiving Systems' Capture Hall Virtual Tour (English) Michael Black

2.3K views - 4 years ago

ROMP: Monocular, One-stage, Regression of Multiple 3D People (ICCV 2021)

ROMP: Monocular, One-stage, Regression of Multiple 3D People (ICCV 2021) Michael Black

4.5K views - 4 years ago

Learning to Regress Bodies using Differentiable Semantic Rendering (ICCV 2021)

Learning to Regress Bodies using Differentiable Semantic Rendering (ICCV 2021) Michael Black

1.4K views - 4 years ago

PARE: Part Attention Regressor for 3D Human Body Estimation (ICCV 2021)

PARE: Part Attention Regressor for 3D Human Body Estimation (ICCV 2021) Michael Black

2.4K views - 4 years ago

SPEC: Seeing People in the Wild with an Estimated Camera (ICCV 2021)

SPEC: Seeing People in the Wild with an Estimated Camera (ICCV 2021) Michael Black

1.8K views - 4 years ago

SOMA: Solving Optical Marker-Based MoCap Automatically (ICCV'2021)

SOMA: Solving Optical Marker-Based MoCap Automatically (ICCV'2021) Michael Black

5K views - 4 years ago

DECA: Siggraph 2021 talk (full version)

DECA: Siggraph 2021 talk (full version) Michael Black

2.4K views - 4 years ago

SAMP: Scene-Aware Motion Prediction (ICCV 2021)

SAMP: Scene-Aware Motion Prediction (ICCV 2021) Michael Black

3.8K views - 4 years ago

SCALE (CVPR'21 Talk Version)

SCALE (CVPR'21 Talk Version) Michael Black

1.1K views - 4 years ago

Putting SMPL into Scenes

Putting SMPL into Scenes Michael Black

1.8K views - 4 years ago

SMPL made Simple -- Introduction

SMPL made Simple -- Introduction Michael Black

29.9K views - 4 years ago

SMPL: Frequently Asked Questions

SMPL: Frequently Asked Questions Michael Black

4.7K views - 4 years ago

Problems with SMPL and fixing them with STAR

Problems with SMPL and fixing them with STAR Michael Black

2.4K views - 4 years ago

Visual Imitation with SMPL

Visual Imitation with SMPL Michael Black

1.8K views - 4 years ago

Clothing SMPL Michael Black

6.1K views - 4 years ago

SMPL in Human Health

SMPL in Human Health Michael Black

1K views - 4 years ago

SMPL at Meshcapade: Digital Humans made Easy

SMPL at Meshcapade: Digital Humans made Easy Michael Black

4K views - 4 years ago

SMPLpix: Combining SMPL and Neural Rendering

SMPLpix: Combining SMPL and Neural Rendering Michael Black

3.6K views - 4 years ago

VIBE: Video Inference for human Body pose and shape Estimation

VIBE: Video Inference for human Body pose and shape Estimation Michael Black

2.3K views - 4 years ago

Robots and SMPL: Combining ROS and Unreal using Julia

Robots and SMPL: Combining ROS and Unreal using Julia Michael Black

3.9K views - 4 years ago

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

SMPL-X Application Integrations. Using SMPL-X in Blender, Unity and Unreal Michael Black

21.2K views - 4 years ago

SMPL in VR and AR

SMPL in VR and AR Michael Black

1.7K views - 4 years ago

Datasets of and for SMPL and related models

Datasets of and for SMPL and related models Michael Black

3K views - 4 years ago

SMPL from Images via Optimization

SMPL from Images via Optimization Michael Black

6.8K views - 4 years ago

Regressing SMPL from Images

Regressing SMPL from Images Michael Black

4.7K views - 4 years ago

SMPL in Maya Michael Black

2.1K views - 4 years ago

TUCH: On Self-Contact and Human Pose (CVPR 2021)

TUCH: On Self-Contact and Human Pose (CVPR 2021) Michael Black

2.3K views - 4 years ago