SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising

2026-05-26

AI Summary

This work addresses the challenge of ambiguous point-to-surface correspondence in unsupervised point cloud denoising caused by noise interference. To resolve this, the authors propose Self-Induced Mirror Point Consistency (SIMPC), a novel approach that introduces a geometric prior based on mirror points. For each noisy point, SIMPC generates its mirror counterpart with respect to the underlying latent surface and enforces a self-induced consistency constraint that aligns the denoised positions of the original and mirror points. This mechanism establishes a deterministic, unsupervised correspondence without relying on statistical mappings, thereby avoiding the ambiguities inherent in conventional methods. Extensive experiments demonstrate that SIMPC significantly outperforms existing unsupervised techniques on both synthetic and real-world datasets, and even surpasses several strong supervised baselines.

Abstract

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.

Problem

• point cloud denoising
• unsupervised learning
• correspondence ambiguity
• noise perturbation
• geometric consistency

Innovation

• Self-Induced Mirror-Point Consistency
• unsupervised point cloud denoising
• mirror-point generation
• geometric priors
• deterministic correspondence