Noise2Score3D:Unsupervised Tweedie's Approach for Point Cloud Denoising
This addresses the problem of limited clean data availability for point cloud denoising in 3D vision applications, offering an incremental improvement over existing unsupervised methods.
The paper tackles point cloud denoising without needing clean training data by proposing Noise2Score3D, an unsupervised framework that learns the gradient of the underlying distribution from noisy data using Tweedie's formula; it achieves state-of-the-art performance on benchmarks, outperforming other unsupervised methods in Chamfer distance and point-to-mesh metrics, and rivals some supervised approaches.
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.