SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
This work addresses the problem of unsupervised point cloud denoising, a key challenge in 3D vision, by reducing correspondence ambiguity without requiring clean data.
SIMPC introduces a self-supervised method for point cloud denoising that learns deterministic correspondences between noisy points and the underlying surface using mirror-point consistency, outperforming state-of-the-art unsupervised methods and surpassing several supervised counterparts on synthetic and real-world datasets.
In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction more challenging than in images. Existing methods impose statistical mappings across noisy variants via noise or optimal transport, but suffer from correspondence ambiguity. In this work, we propose Self-Induced Mirror-Point Consistency (SIMPC) to learn deterministic correspondences between points and the underlying surface in an unsupervised manner. For each noisy point, SIMPC generates a mirror-point on the opposite side of the underlying surface, guided by geometric priors during the denoising process. By encouraging consistency between the denoising targets of the original point and its mirror counterpart, SIMPC effectively localizes the position of underlying surface. Extensive experiments on synthetic and real-world datasets demonstrate that SIMPC significantly outperforms state-of-the-art unsupervised methods and surpasses several strong supervised counterparts.