U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching

TL;DR

U-CAN is an unsupervised point cloud denoising framework that leverages consistency-aware noise-to-noise matching, enabling effective denoising without requiring clean ground truth data, and also benefits 2D image denoising.

Contribution

The paper introduces a novel unsupervised denoising method with a consistency-aware loss and noise-to-noise matching, applicable to both 3D point clouds and 2D images.

Findings

Significant improvements over state-of-the-art unsupervised methods in point cloud denoising.

Comparable results to supervised methods in point cloud denoising.

The proposed constraint benefits both 3D and 2D denoising tasks.

Abstract

Point clouds captured by scanning sensors are often perturbed by noise, which have a highly negative impact on downstream tasks (e.g. surface reconstruction and shape understanding). Previous works mostly focus on training neural networks with noisy-clean point cloud pairs for learning denoising priors, which requires extensively manual efforts. In this work, we introduce U-CAN, an Unsupervised framework for point cloud denoising with Consistency-Aware Noise2Noise matching. Specifically, we leverage a neural network to infer a multi-step denoising path for each point of a shape or scene with a noise to noise matching scheme. We achieve this by a novel loss which enables statistical reasoning on multiple noisy point cloud observations. We further introduce a novel constraint on the denoised geometry consistency for learning consistency-aware denoising patterns. We justify that the proposed constraint is a general term which is not limited to 3D domain and can also contribute to the area of 2D image denoising. Our evaluations under the widely used benchmarks in point cloud denoising, upsampling and image denoising show significant improvement over the state-of-the-art unsupervised methods, where U-CAN also produces comparable results with the supervised methods.