Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.14804 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909996774588416 |
|---|---|
| author | Weißberg, Tobias Wang, Weikang Roetzer, Paul Amrani, Nafie El Bernard, Florian |
| author_facet | Weißberg, Tobias Wang, Weikang Roetzer, Paul Amrani, Nafie El Bernard, Florian |
| contents | Shape descriptors, i.e., per-vertex features of 3D meshes or point clouds, are fundamental to shape analysis. Historically, various handcrafted geometry-aware descriptors and feature refinement techniques have been proposed. Recently, several studies have initiated a new research direction by leveraging features from image foundation models to create semantics-aware descriptors, demonstrating advantages across tasks like shape matching, editing, and segmentation. Symmetry, another key concept in shape analysis, has also attracted increasing attention. Consequently, constructing symmetry-aware shape descriptors is a natural progression. Although the recent method $χ$ (Wang et al., 2025) successfully extracted symmetry-informative features from semantic-aware descriptors, its features are only one-dimensional, neglecting other valuable semantic information. Furthermore, the extracted symmetry-informative feature is usually noisy and yields small misclassified patches. To address these gaps, we propose a feature disentanglement approach which is simultaneously symmetry informative and symmetry agnostic. Further, we propose a feature refinement technique to improve the robustness of predicted symmetry informative features. Extensive experiments, including intrinsic symmetry detection, left/right classification, and shape matching, demonstrate the effectiveness of our proposed framework compared to various state-of-the-art methods, both qualitatively and quantitatively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14804 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Symmetry Informative and Agnostic Feature Disentanglement for 3D Shapes Weißberg, Tobias Wang, Weikang Roetzer, Paul Amrani, Nafie El Bernard, Florian Computer Vision and Pattern Recognition Shape descriptors, i.e., per-vertex features of 3D meshes or point clouds, are fundamental to shape analysis. Historically, various handcrafted geometry-aware descriptors and feature refinement techniques have been proposed. Recently, several studies have initiated a new research direction by leveraging features from image foundation models to create semantics-aware descriptors, demonstrating advantages across tasks like shape matching, editing, and segmentation. Symmetry, another key concept in shape analysis, has also attracted increasing attention. Consequently, constructing symmetry-aware shape descriptors is a natural progression. Although the recent method $χ$ (Wang et al., 2025) successfully extracted symmetry-informative features from semantic-aware descriptors, its features are only one-dimensional, neglecting other valuable semantic information. Furthermore, the extracted symmetry-informative feature is usually noisy and yields small misclassified patches. To address these gaps, we propose a feature disentanglement approach which is simultaneously symmetry informative and symmetry agnostic. Further, we propose a feature refinement technique to improve the robustness of predicted symmetry informative features. Extensive experiments, including intrinsic symmetry detection, left/right classification, and shape matching, demonstrate the effectiveness of our proposed framework compared to various state-of-the-art methods, both qualitatively and quantitatively. |
| title | Symmetry Informative and Agnostic Feature Disentanglement for 3D Shapes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.14804 |