Joint Symmetry Detection and Shape Matching for Non-Rigid Point Cloud
This addresses a major challenge in non-rigid 3D shape matching where symmetry mismatch causes errors, benefiting computer vision and graphics applications.
The paper tackles the problem of simultaneously detecting self-symmetry and performing shape matching for non-rigid point clouds, which was previously unaddressed in learning frameworks. The proposed method outperforms competitive baselines on multiple benchmarks.
Despite the success of deep functional maps in non-rigid 3D shape matching, there exists no learning framework that models both self-symmetry and shape matching simultaneously. This is despite the fact that errors due to symmetry mismatch are a major challenge in non-rigid shape matching. In this paper, we propose a novel framework that simultaneously learns both self symmetry as well as a pairwise map between a pair of shapes. Our key idea is to couple a self symmetry map and a pairwise map through a regularization term that provides a joint constraint on both of them, thereby, leading to more accurate maps. We validate our method on several benchmarks where it outperforms many competitive baselines on both tasks.