无需干净数据，一键去除点云噪声，速度更快效果更优。
Noise2Score3D:Unsupervised Tweedie's Approach for Point Cloud Denoising
- 直接从噪声数据中学习点云分布梯度，无需配对干净样本。
- 在标准测试集上超越现有无监督方法，接近有监督模型表现。
- 可自动估计噪声参数，适合真实场景复杂噪声处理。
基于贝叶斯统计与图像去噪最新进展，我们提出 Noise2Score3D，一种完全无监督的点云去噪框架，解决清洁数据稀缺的核心难题。该方法直接从噪声数据中学习点云分布的梯度，训练无需清洁数据。通过引入 Tweedie 公式，推理仅需单步完成，避免现有无监督方法的迭代过程，显著提升性能与效率。实验表明，Noise2Score3D 在标准基准上达到领先水平，优于其他无监督方法，在 Chamfer 距离与 point-to-mesh 指标上表现突出，甚至媲美部分有监督方法。同时具备强泛化能力，适用于训练数据之外的场景。此外，我们提出 Point Cloud 总变差（Total Variation for Point Cloud），可估计未知噪声参数，进一步增强方法的实用性和适应性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。