Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.09305 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916117425946624 |
|---|---|
| author | Tang, Boshi Wang, Jianan Wu, Zhiyong Zhang, Lei |
| author_facet | Tang, Boshi Wang, Jianan Wu, Zhiyong Zhang, Lei |
| contents | Although Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation, a comprehensive understanding of its formulation is still lacking, hindering the development of 3D generation. In this work, we decompose SDS as a combination of three functional components, namely mode-seeking, mode-disengaging and variance-reducing terms, analyzing the properties of each. We show that problems such as over-smoothness and implausibility result from the intrinsic deficiency of the first two terms and propose a more advanced variance-reducing term than that introduced by SDS. Based on the analysis, we propose a simple yet effective approach named Stable Score Distillation (SSD) which strategically orchestrates each term for high-quality 3D generation and can be readily incorporated to various 3D generation frameworks and 3D representations. Extensive experiments validate the efficacy of our approach, demonstrating its ability to generate high-fidelity 3D content without succumbing to issues such as over-smoothness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09305 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Stable Score Distillation for High-Quality 3D Generation Tang, Boshi Wang, Jianan Wu, Zhiyong Zhang, Lei Computer Vision and Pattern Recognition Although Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation, a comprehensive understanding of its formulation is still lacking, hindering the development of 3D generation. In this work, we decompose SDS as a combination of three functional components, namely mode-seeking, mode-disengaging and variance-reducing terms, analyzing the properties of each. We show that problems such as over-smoothness and implausibility result from the intrinsic deficiency of the first two terms and propose a more advanced variance-reducing term than that introduced by SDS. Based on the analysis, we propose a simple yet effective approach named Stable Score Distillation (SSD) which strategically orchestrates each term for high-quality 3D generation and can be readily incorporated to various 3D generation frameworks and 3D representations. Extensive experiments validate the efficacy of our approach, demonstrating its ability to generate high-fidelity 3D content without succumbing to issues such as over-smoothness. |
| title | Stable Score Distillation for High-Quality 3D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.09305 |