RINO: Rotation-Invariant Non-Rigid Correspondences
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918415344599040 |
|---|---|
| author | Gao, Maolin Hu-Chen, Shao Jie Deng, Congyue Marin, Riccardo Guibas, Leonidas Cremers, Daniel |
| author_facet | Gao, Maolin Hu-Chen, Shao Jie Deng, Congyue Marin, Riccardo Guibas, Leonidas Cremers, Daniel |
| contents | Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27773 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RINO: Rotation-Invariant Non-Rigid Correspondences Gao, Maolin Hu-Chen, Shao Jie Deng, Congyue Marin, Riccardo Guibas, Leonidas Cremers, Daniel Computer Vision and Pattern Recognition Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcrafted descriptors, limiting their effectiveness under non-isometric deformations, partial data, and non-manifold inputs. To overcome these issues, we introduce RINO, an unsupervised, rotation-invariant dense correspondence framework that effectively unifies rigid and non-rigid shape matching. The core of our method is the novel RINONet, a feature extractor that integrates vector-based SO(3)-invariant learning with orientation-aware complex functional maps to extract robust features directly from raw geometry. This allows for a fully end-to-end, data-driven approach that bypasses the need for shape pre-alignment or handcrafted features. Extensive experiments show unprecedented performance of RINO across challenging non-rigid matching tasks, including arbitrary poses, non-isometry, partiality, non-manifoldness, and noise. |
| title | RINO: Rotation-Invariant Non-Rigid Correspondences |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27773 |