Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.00862 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918423632543744 |
|---|---|
| author | Sapoutzoglou, Panagiotis Terzakis, George Floros, Georgios Pateraki, Maria |
| author_facet | Sapoutzoglou, Panagiotis Terzakis, George Floros, Georgios Pateraki, Maria |
| contents | Traditional explicit 3D representations, such as point clouds and meshes, demand significant storage to capture fine geometric details and require complex indexing systems for surface lookups, making functional representations an efficient, compact, and continuous alternative. In this work, we propose a novel, object-specific functional shape representation that models surface geometry with Gaussian Process (GP) mixture models. Rather than relying on computationally heavy neural architectures, our method is lightweight, leveraging GPs to learn continuous directional distance fields from sparsely sampled point clouds. We capture complex topologies by anchoring local GP priors at strategic reference points, which can be flexibly extracted using any structural decomposition method (e.g. skeletonization, distance-based clustering). Extensive evaluations on the ShapeNetCore and IndustryShapes datasets demonstrate that our method can efficiently and accurately represent complex geometries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00862 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Shape Representation using Gaussian Process mixture models Sapoutzoglou, Panagiotis Terzakis, George Floros, Georgios Pateraki, Maria Computer Vision and Pattern Recognition Traditional explicit 3D representations, such as point clouds and meshes, demand significant storage to capture fine geometric details and require complex indexing systems for surface lookups, making functional representations an efficient, compact, and continuous alternative. In this work, we propose a novel, object-specific functional shape representation that models surface geometry with Gaussian Process (GP) mixture models. Rather than relying on computationally heavy neural architectures, our method is lightweight, leveraging GPs to learn continuous directional distance fields from sparsely sampled point clouds. We capture complex topologies by anchoring local GP priors at strategic reference points, which can be flexibly extracted using any structural decomposition method (e.g. skeletonization, distance-based clustering). Extensive evaluations on the ShapeNetCore and IndustryShapes datasets demonstrate that our method can efficiently and accurately represent complex geometries. |
| title | Shape Representation using Gaussian Process mixture models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00862 |