| Name: | Haoxuan Li |
|---|---|
| Position: | Ph.D Candidate |
| E-Mail: | haoxuan.li@tum.de |
| Phone: | TBD |
| Room No: | 02.07.034 |
Bio
Haoxuan Li is a Ph.D. candidate at TUM Visual Computing Group, advised by Prof. Dr. Matthias Niessner. Before this, he received his Master's degree at the Technical University of Munich and his Bachelor's degree at the Shanghai Jiao Tong University.Research Interest
3D reconstruction, 3D generationPublications
2024
| SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors |
|---|
| Dave Zhenyu Chen, Haoxuan Li, Hsin-Ying Lee, Sergey Tulyakov, Matthias Nießner |
| CVPR 2024 |
| We propose SceneTex, a novel method for effectively generating high-quality and style-consistent textures for indoor scenes using depth-to-image diffusion priors. At its core, SceneTex proposes a multiresolution texture field to implicitly encode the mesh appearance. To further secure the style consistency across views, we introduce a cross-attention decoder to predict the RGB values by cross-attending to the pre-sampled reference locations in each instance. |
| [video][bibtex][project page] |