Symmetry Informative and Agnostic Feature Disentanglement for 3D Shapes

TL;DR

This paper introduces a novel feature disentanglement and refinement framework for 3D shape descriptors, enhancing symmetry-awareness and robustness, leading to improved shape analysis tasks like matching and segmentation.

Contribution

It proposes a symmetry-aware and agnostic feature disentanglement method with a refinement technique, addressing noise and limited semantic information in existing symmetry-informative features.

Findings

Improved symmetry detection accuracy

Enhanced shape matching performance

Robustness against noisy symmetry features

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.