DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917973111865344 |
|---|---|
| author | Deng, Ken Guo, Yuan-Chen Sun, Jingxiang Zou, Zi-Xin Li, Yangguang Cai, Xin Cao, Yan-Pei Liu, Yebin Liang, Ding |
| author_facet | Deng, Ken Guo, Yuan-Chen Sun, Jingxiang Zou, Zi-Xin Li, Yangguang Cai, Xin Cao, Yan-Pei Liu, Yebin Liang, Ding |
| contents | Modern 3D generation methods can rapidly create shapes from sparse or single views, but their outputs often lack geometric detail due to computational constraints. We present DetailGen3D, a generative approach specifically designed to enhance these generated 3D shapes. Our key insight is to model the coarse-to-fine transformation directly through data-dependent flows in latent space, avoiding the computational overhead of large-scale 3D generative models. We introduce a token matching strategy that ensures accurate spatial correspondence during refinement, enabling local detail synthesis while preserving global structure. By carefully designing our training data to match the characteristics of synthesized coarse shapes, our method can effectively enhance shapes produced by various 3D generation and reconstruction approaches, from single-view to sparse multi-view inputs. Extensive experiments demonstrate that DetailGen3D achieves high-fidelity geometric detail synthesis while maintaining efficiency in training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16820 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow Deng, Ken Guo, Yuan-Chen Sun, Jingxiang Zou, Zi-Xin Li, Yangguang Cai, Xin Cao, Yan-Pei Liu, Yebin Liang, Ding Computer Vision and Pattern Recognition Graphics Modern 3D generation methods can rapidly create shapes from sparse or single views, but their outputs often lack geometric detail due to computational constraints. We present DetailGen3D, a generative approach specifically designed to enhance these generated 3D shapes. Our key insight is to model the coarse-to-fine transformation directly through data-dependent flows in latent space, avoiding the computational overhead of large-scale 3D generative models. We introduce a token matching strategy that ensures accurate spatial correspondence during refinement, enabling local detail synthesis while preserving global structure. By carefully designing our training data to match the characteristics of synthesized coarse shapes, our method can effectively enhance shapes produced by various 3D generation and reconstruction approaches, from single-view to sparse multi-view inputs. Extensive experiments demonstrate that DetailGen3D achieves high-fidelity geometric detail synthesis while maintaining efficiency in training. |
| title | DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2411.16820 |