Noise2Score3D:Unsupervised Tweedie's Approach for Point Cloud Denoising

TL;DR

Noise2Score3D is an unsupervised point cloud denoising method that uses Tweedie's formula to learn directly from noisy data, achieving state-of-the-art results without requiring clean training data.

Contribution

It introduces a novel unsupervised framework leveraging Tweedie's formula for efficient point cloud denoising, eliminating the need for clean data and improving performance.

Findings

Outperforms existing unsupervised methods in benchmarks

Achieves competitive results with supervised approaches

Demonstrates strong generalization to unseen datasets

Abstract

Building on recent advances in Bayesian statistics and image denoising, we propose Noise2Score3D, a fully unsupervised framework for point cloud denoising that addresses the critical challenge of limited availability of clean data. Noise2Score3D learns the gradient of the underlying point cloud distribution directly from noisy data, eliminating the need for clean data during training. By leveraging Tweedie's formula, our method performs inference in a single step, avoiding the iterative processes used in existing unsupervised methods, thereby improving both performance and efficiency. Experimental results demonstrate that Noise2Score3D achieves state-of-the-art performance on standard benchmarks, outperforming other unsupervised methods in Chamfer distance and point-to-mesh metrics, and rivaling some supervised approaches. Furthermore, Noise2Score3D demonstrates strong generalization ability beyond training datasets. Additionally, we introduce Total Variation for Point Cloud, a criterion that allows for the estimation of unknown noise parameters, which further enhances the method's versatility and real-world utility.