Picture for Hsin-Ying Lee

Hsin-Ying Lee

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models

Add code
Jun 11, 2024
Viaarxiv icon

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

Jun 09, 2024
Viaarxiv icon

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

Add code
May 28, 2024
Viaarxiv icon

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

Add code
Feb 29, 2024
Viaarxiv icon

Visual Concept-driven Image Generation with Text-to-Image Diffusion Model

Feb 18, 2024
Viaarxiv icon

AToM: Amortized Text-to-Mesh using 2D Diffusion

Add code
Feb 01, 2024
Figure 1 for AToM: Amortized Text-to-Mesh using 2D Diffusion
Figure 2 for AToM: Amortized Text-to-Mesh using 2D Diffusion
Figure 3 for AToM: Amortized Text-to-Mesh using 2D Diffusion
Figure 4 for AToM: Amortized Text-to-Mesh using 2D Diffusion
Viaarxiv icon

Diffusion Priors for Dynamic View Synthesis from Monocular Videos

Add code
Jan 10, 2024
Viaarxiv icon

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

Add code
Jan 04, 2024
Viaarxiv icon

Virtual Pets: Animatable Animal Generation in 3D Scenes

Add code
Dec 21, 2023
Viaarxiv icon

SceneWiz3D: Towards Text-guided 3D Scene Composition

Add code
Dec 13, 2023
Viaarxiv icon