Latest

• Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions
• COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation
• GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning
• PACE: Human and Camera Motion Estimation from in-the-wild Videos
• Learning Human Dynamics in Autonomous Driving Scenarios
• PhysDiff: Physics-Guided Human Motion Diffusion Model
• Learning Physically Simulated Tennis Players from Broadcast Videos
• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
• RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control
• Embodied Scene-aware Human Pose Estimation
• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras