Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches
This addresses the problem of detecting partial symmetries for tasks like 3D geometry completion and segmentation, representing an incremental advance as it introduces a self-supervised data-driven approach to a known challenge.
The paper tackles partial extrinsic symmetry detection in 3D geometry by learning invariant local shape features using contrastive learning on geodesic point cloud patches, and demonstrates the method's ability to extract multiple solutions and generalize across datasets.
Symmetry detection, especially partial and extrinsic symmetry, is essential for various downstream tasks, like 3D geometry completion, segmentation, compression and structure-aware shape encoding or generation. In order to detect partial extrinsic symmetries, we propose to learn rotation, reflection, translation and scale invariant local shape features for geodesic point cloud patches via contrastive learning, which are robust across multiple classes and generalize over different datasets. We show that our approach is able to extract multiple valid solutions for this ambiguous problem. Furthermore, we introduce a novel benchmark test for partial extrinsic symmetry detection to evaluate our method. Lastly, we incorporate the detected symmetries together with a region growing algorithm to demonstrate a downstream task with the goal of computing symmetry-aware partitions of 3D shapes. To our knowledge, we are the first to propose a self-supervised data-driven method for partial extrinsic symmetry detection.