EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909136027910144 |
|---|---|
| author | Le, Cindy Hetang, Congrui Lin, Chendi Cao, Ang He, Yihui |
| author_facet | Le, Cindy Hetang, Congrui Lin, Chendi Cao, Ang He, Yihui |
| contents | This paper presents a novel method to generate textures for 3D models given text prompts and 3D meshes. Additional depth information is taken into account to perform the Score Distillation Sampling (SDS) process with depth conditional Stable Diffusion. We ran our model over the open-source dataset Objaverse and conducted a user study to compare the results with those of various 3D texturing methods. We have shown that our model can generate more satisfactory results and produce various art styles for the same object. In addition, we achieved faster time when generating textures of comparable quality. We also conduct thorough ablation studies of how different factors may affect generation quality, including sampling steps, guidance scale, negative prompts, data augmentation, elevation range, and alternatives to SDS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_15573 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth Le, Cindy Hetang, Congrui Lin, Chendi Cao, Ang He, Yihui Computer Vision and Pattern Recognition Graphics This paper presents a novel method to generate textures for 3D models given text prompts and 3D meshes. Additional depth information is taken into account to perform the Score Distillation Sampling (SDS) process with depth conditional Stable Diffusion. We ran our model over the open-source dataset Objaverse and conducted a user study to compare the results with those of various 3D texturing methods. We have shown that our model can generate more satisfactory results and produce various art styles for the same object. In addition, we achieved faster time when generating textures of comparable quality. We also conduct thorough ablation studies of how different factors may affect generation quality, including sampling steps, guidance scale, negative prompts, data augmentation, elevation range, and alternatives to SDS. |
| title | EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2311.15573 |