Picture for Zhiyang Dou

Zhiyang Dou

DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image

Add code
Jun 26, 2024
Viaarxiv icon

AutoCV: Empowering Reasoning with Automated Process Labeling via Confidence Variation

Add code
May 29, 2024
Viaarxiv icon

Part123: Part-aware 3D Reconstruction from a Single-view Image

Add code
May 27, 2024
Figure 1 for Part123: Part-aware 3D Reconstruction from a Single-view Image
Figure 2 for Part123: Part-aware 3D Reconstruction from a Single-view Image
Figure 3 for Part123: Part-aware 3D Reconstruction from a Single-view Image
Figure 4 for Part123: Part-aware 3D Reconstruction from a Single-view Image
Viaarxiv icon

LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment

Add code
Mar 21, 2024
Figure 1 for LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
Figure 2 for LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
Figure 3 for LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
Figure 4 for LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
Viaarxiv icon

Coverage Axis++: Efficient Inner Point Selection for 3D Shape Skeletonization

Add code
Feb 01, 2024
Viaarxiv icon

Disentangled Clothed Avatar Generation from Text Descriptions

Add code
Dec 08, 2023
Viaarxiv icon

Boosting Segment Anything Model Towards Open-Vocabulary Learning

Add code
Dec 06, 2023
Viaarxiv icon

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Motion Generation

Add code
Dec 04, 2023
Figure 1 for EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Motion Generation
Figure 2 for EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Motion Generation
Figure 3 for EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Motion Generation
Figure 4 for EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Motion Generation
Viaarxiv icon

TLControl: Trajectory and Language Control for Human Motion Synthesis

Add code
Nov 30, 2023
Figure 1 for TLControl: Trajectory and Language Control for Human Motion Synthesis
Figure 2 for TLControl: Trajectory and Language Control for Human Motion Synthesis
Figure 3 for TLControl: Trajectory and Language Control for Human Motion Synthesis
Figure 4 for TLControl: Trajectory and Language Control for Human Motion Synthesis
Viaarxiv icon

Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models

Add code
Nov 28, 2023
Figure 1 for Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models
Figure 2 for Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models
Figure 3 for Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models
Figure 4 for Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models
Viaarxiv icon