ChatHuman: Reasoning about 3D humans and their behavior

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

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

3D human motion capture from video with MoCapade3.0

SMPL-X capture and transfer to G1

PromptHMR: Promptable Human Mesh Recovery (CVPR 2025)

CameraHMR: Aligning People with Perspective (3DV 2025)

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

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

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

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

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

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

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

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

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

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

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

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)

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation

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)

Meta-commerce in the Age of Avatars

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

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

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

OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022)

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

Perceiving Systems: 2016-2021

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

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

Perceiving Systems' Capture Hall Virtual Tour (English)

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

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

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

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

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

DECA: Siggraph 2021 talk (full version)

SAMP: Scene-Aware Motion Prediction (ICCV 2021)

SCALE (CVPR'21 Talk Version)

Putting SMPL into Scenes

SMPL made Simple -- Introduction

SMPL: Frequently Asked Questions

Problems with SMPL and fixing them with STAR

Visual Imitation with SMPL

Clothing SMPL

SMPL in Human Health

SMPL at Meshcapade: Digital Humans made Easy

SMPLpix: Combining SMPL and Neural Rendering

VIBE: Video Inference for human Body pose and shape Estimation

Robots and SMPL: Combining ROS and Unreal using Julia

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

SMPL in VR and AR

Datasets of and for SMPL and related models

SMPL from Images via Optimization

Regressing SMPL from Images

SMPL in Maya

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

AGORA human pose and shape dataset (CVPR 2021)