Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.12721 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915496594505728 |
|---|---|
| author | Zhang, Jingdong Chen, Weikai Liu, Yuan Wang, Jionghao Yu, Zhengming Shen, Zhuowen Yang, Bo Wang, Wenping Li, Xin |
| author_facet | Zhang, Jingdong Chen, Weikai Liu, Yuan Wang, Jionghao Yu, Zhengming Shen, Zhuowen Yang, Bo Wang, Wenping Li, Xin |
| contents | Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or nontrivial topologies. In particular, we encode geometry information by projecting it onto a bounding sphere and unwrapping it into a compact and structural multi-layer 2D Spherical Projection (SP) representation. Operating solely in the image domain, SPGen offers three key advantages simultaneously: (1) Consistency. The injective SP mapping encodes surface geometry with a single viewpoint which naturally eliminates view inconsistency and ambiguity; (2) Flexibility. Multi-layer SP maps represent nested internal structures and support direct lifting to watertight or open 3D surfaces; (3) Efficiency. The image-domain formulation allows the direct inheritance of powerful 2D diffusion priors and enables efficient finetuning with limited computational resources. Extensive experiments demonstrate that SPGen significantly outperforms existing baselines in geometric quality and computational efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12721 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation Zhang, Jingdong Chen, Weikai Liu, Yuan Wang, Jionghao Yu, Zhengming Shen, Zhuowen Yang, Bo Wang, Wenping Li, Xin Computer Vision and Pattern Recognition Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or nontrivial topologies. In particular, we encode geometry information by projecting it onto a bounding sphere and unwrapping it into a compact and structural multi-layer 2D Spherical Projection (SP) representation. Operating solely in the image domain, SPGen offers three key advantages simultaneously: (1) Consistency. The injective SP mapping encodes surface geometry with a single viewpoint which naturally eliminates view inconsistency and ambiguity; (2) Flexibility. Multi-layer SP maps represent nested internal structures and support direct lifting to watertight or open 3D surfaces; (3) Efficiency. The image-domain formulation allows the direct inheritance of powerful 2D diffusion priors and enables efficient finetuning with limited computational resources. Extensive experiments demonstrate that SPGen significantly outperforms existing baselines in geometric quality and computational efficiency. |
| title | SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.12721 |