Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.10947 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913579791286272 |
|---|---|
| author | Wu, Haoyu Karumuri, Meher Gitika Zou, Chuhang Bang, Seungbae Li, Yuelong Samaras, Dimitris Hadap, Sunil |
| author_facet | Wu, Haoyu Karumuri, Meher Gitika Zou, Chuhang Bang, Seungbae Li, Yuelong Samaras, Dimitris Hadap, Sunil |
| contents | Current image-to-3D approaches suffer from high computational costs and lack scalability for high-resolution outputs. In contrast, we introduce a novel framework to directly generate explicit surface geometry and texture using multi-view 2D depth and RGB images along with 3D Gaussian features using a repurposed Stable Diffusion model. We introduce a depth branch into U-Net for efficient and high quality multi-view, cross-domain generation and incorporate epipolar attention into the latent-to-pixel decoder for pixel-level multi-view consistency. By back-projecting the generated depth pixels into 3D space, we create a structured 3D representation that can be either rendered via Gaussian splatting or extracted to high-quality meshes, thereby leveraging additional novel view synthesis loss to further improve our performance. Extensive experiments demonstrate that our method surpasses existing baselines in geometry and texture quality while achieving significantly faster generation time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10947 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Direct and Explicit 3D Generation from a Single Image Wu, Haoyu Karumuri, Meher Gitika Zou, Chuhang Bang, Seungbae Li, Yuelong Samaras, Dimitris Hadap, Sunil Computer Vision and Pattern Recognition Current image-to-3D approaches suffer from high computational costs and lack scalability for high-resolution outputs. In contrast, we introduce a novel framework to directly generate explicit surface geometry and texture using multi-view 2D depth and RGB images along with 3D Gaussian features using a repurposed Stable Diffusion model. We introduce a depth branch into U-Net for efficient and high quality multi-view, cross-domain generation and incorporate epipolar attention into the latent-to-pixel decoder for pixel-level multi-view consistency. By back-projecting the generated depth pixels into 3D space, we create a structured 3D representation that can be either rendered via Gaussian splatting or extracted to high-quality meshes, thereby leveraging additional novel view synthesis loss to further improve our performance. Extensive experiments demonstrate that our method surpasses existing baselines in geometry and texture quality while achieving significantly faster generation time. |
| title | Direct and Explicit 3D Generation from a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.10947 |