Symmetry Informative and Agnostic Feature Disentanglement for 3D Shapes

2026-01-21

AI Summary

This work addresses the limitations of existing methods for constructing symmetry-aware 3D shape descriptors, which typically rely solely on one-dimensional symmetry cues, neglect rich semantic information, and are highly susceptible to noise—often leading to misclassification. To overcome these issues, we propose a feature disentanglement framework that, for the first time, jointly models symmetry-related and symmetry-irrelevant semantic features. Our approach incorporates a symmetry-guided refinement mechanism that significantly enhances the robustness and accuracy of symmetry representation. Leveraging semantic features extracted from image foundation models, the method generates per-vertex descriptors applicable to both 3D meshes and point clouds. Extensive experiments demonstrate consistent state-of-the-art performance across multiple tasks, including intrinsic symmetry detection, left-right classification, and shape matching.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Feature Construction/Reformulation
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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 $\chi$ (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.

Problem

• symmetry-aware descriptors
• feature disentanglement
• 3D shape analysis
• semantic-aware features
• intrinsic symmetry

Innovation

• feature disentanglement
• symmetry-aware descriptor
• 3D shape analysis
• semantic-aware features
• feature refinement