Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.09149 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910925870596096 |
|---|---|
| author | Li, Changhao Xin, Yu Zhou, Xiaowei Shamir, Ariel Zhang, Hao Liu, Ligang Hu, Ruizhen |
| author_facet | Li, Changhao Xin, Yu Zhou, Xiaowei Shamir, Ariel Zhang, Hao Liu, Ligang Hu, Ruizhen |
| contents | We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the importance of perceptual shape understanding for learning 3D shapes, MASH represents a 3D shape as a collection of observable local surface patches, each defined by a spherical distance function emanating from an anchor point. We further leverage the compactness of spherical harmonics to encode the MASH functions, combined with a generalized view cone with a parameterized base that masks the spatial extent of the spherical function to attain locality. We develop a differentiable optimization algorithm capable of converting any point cloud into a MASH representation accurately approximating ground-truth surfaces with arbitrary geometry and topology. Extensive experiments demonstrate that MASH is versatile for multiple applications including surface reconstruction, shape generation, completion, and blending, achieving superior performance thanks to its unique representation encompassing both implicit and explicit features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation Li, Changhao Xin, Yu Zhou, Xiaowei Shamir, Ariel Zhang, Hao Liu, Ligang Hu, Ruizhen Computer Vision and Pattern Recognition Computational Geometry We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the importance of perceptual shape understanding for learning 3D shapes, MASH represents a 3D shape as a collection of observable local surface patches, each defined by a spherical distance function emanating from an anchor point. We further leverage the compactness of spherical harmonics to encode the MASH functions, combined with a generalized view cone with a parameterized base that masks the spatial extent of the spherical function to attain locality. We develop a differentiable optimization algorithm capable of converting any point cloud into a MASH representation accurately approximating ground-truth surfaces with arbitrary geometry and topology. Extensive experiments demonstrate that MASH is versatile for multiple applications including surface reconstruction, shape generation, completion, and blending, achieving superior performance thanks to its unique representation encompassing both implicit and explicit features. |
| title | MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation |
| topic | Computer Vision and Pattern Recognition Computational Geometry |
| url | https://arxiv.org/abs/2504.09149 |