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

SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising arXiv:2605.26894v1 Announce Type: new 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-I