Picture for Donglai Xiang

Donglai Xiang

PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond

Add code
Apr 15, 2025
Viaarxiv icon

Articulated Kinematics Distillation from Video Diffusion Models

Add code
Apr 01, 2025
Viaarxiv icon

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

Add code
Mar 27, 2025
Viaarxiv icon

Edify 3D: Scalable High-Quality 3D Asset Generation

Add code
Nov 11, 2024
Figure 1 for Edify 3D: Scalable High-Quality 3D Asset Generation
Figure 2 for Edify 3D: Scalable High-Quality 3D Asset Generation
Figure 3 for Edify 3D: Scalable High-Quality 3D Asset Generation
Figure 4 for Edify 3D: Scalable High-Quality 3D Asset Generation
Viaarxiv icon

DressRecon: Freeform 4D Human Reconstruction from Monocular Video

Add code
Sep 30, 2024
Figure 1 for DressRecon: Freeform 4D Human Reconstruction from Monocular Video
Figure 2 for DressRecon: Freeform 4D Human Reconstruction from Monocular Video
Figure 3 for DressRecon: Freeform 4D Human Reconstruction from Monocular Video
Figure 4 for DressRecon: Freeform 4D Human Reconstruction from Monocular Video
Viaarxiv icon

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations

Add code
Apr 09, 2024
Figure 1 for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Figure 2 for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Figure 3 for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Figure 4 for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Viaarxiv icon

Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration

Add code
Nov 10, 2023
Figure 1 for Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
Figure 2 for Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
Figure 3 for Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
Figure 4 for Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
Viaarxiv icon

Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input

Add code
Oct 11, 2023
Figure 1 for Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input
Figure 2 for Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input
Figure 3 for Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input
Figure 4 for Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input
Viaarxiv icon

Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing

Add code
Jun 30, 2022
Figure 1 for Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
Figure 2 for Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
Figure 3 for Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
Figure 4 for Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
Viaarxiv icon

Garment Avatars: Realistic Cloth Driving using Pattern Registration

Add code
Jun 07, 2022
Figure 1 for Garment Avatars: Realistic Cloth Driving using Pattern Registration
Figure 2 for Garment Avatars: Realistic Cloth Driving using Pattern Registration
Figure 3 for Garment Avatars: Realistic Cloth Driving using Pattern Registration
Figure 4 for Garment Avatars: Realistic Cloth Driving using Pattern Registration
Viaarxiv icon