Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.11535 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909500844277760 |
|---|---|
| author | Huang, Nan Zhang, Ting Yuan, Yuhui Chen, Dong Zhang, Shanghang |
| author_facet | Huang, Nan Zhang, Ting Yuan, Yuhui Chen, Dong Zhang, Shanghang |
| contents | In this paper, we address the critical bottleneck in robotics caused by the scarcity of diverse 3D data by presenting a novel two-stage approach for generating high-quality 3D models from a single image. This method is motivated by the need to efficiently expand 3D asset creation, particularly for robotics datasets, where the variety of object types is currently limited compared to general image datasets. Unlike previous methods that primarily rely on general diffusion priors, which often struggle to align with the reference image, our approach leverages subject-specific prior knowledge. By incorporating subject-specific priors in both geometry and texture, we ensure precise alignment between the generated 3D content and the reference object. Specifically, we introduce a shading mode-aware prior into the NeRF optimization process, enhancing the geometry and refining texture in the coarse outputs to achieve superior quality. Extensive experiments demonstrate that our method significantly outperforms prior approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_11535 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior Huang, Nan Zhang, Ting Yuan, Yuhui Chen, Dong Zhang, Shanghang Computer Vision and Pattern Recognition Artificial Intelligence In this paper, we address the critical bottleneck in robotics caused by the scarcity of diverse 3D data by presenting a novel two-stage approach for generating high-quality 3D models from a single image. This method is motivated by the need to efficiently expand 3D asset creation, particularly for robotics datasets, where the variety of object types is currently limited compared to general image datasets. Unlike previous methods that primarily rely on general diffusion priors, which often struggle to align with the reference image, our approach leverages subject-specific prior knowledge. By incorporating subject-specific priors in both geometry and texture, we ensure precise alignment between the generated 3D content and the reference object. Specifically, we introduce a shading mode-aware prior into the NeRF optimization process, enhancing the geometry and refining texture in the coarse outputs to achieve superior quality. Extensive experiments demonstrate that our method significantly outperforms prior approaches. |
| title | High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2312.11535 |