深度点云去噪文章整理_score-based point cloud denoising

点云去噪与二维图像去噪不同，点云去噪目前仍是传统方法与深度学习方法并行的领域，不能说哪个是更先进的。但是深度学习作为一种学习工具，被用于点云去噪领域是一个很有价值的方向。下面是最近几年有关于使用深度学习来进行点云去噪的论文。

一、2019年
1、3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation.ICASSP 2019: 8553-8557.[paper]
2、PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds.Comput. Graph. Forum 39(1): 185-203 (2020).[paper]
3、Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning. ICCV 2019: 52-60.[paper]
4、DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense. ICCV 2019: 1961-1970.[paper]

二、2020年
1、Learning Graph-Convolutional Representations for Point Cloud Denoising. ECCV (20) 2020: 103-118.[paper]
2、Differentiable Manifold Reconstruction for Point Cloud Denoising. ACM Multimedia 2020: 1330-1338.[paper]

三、2021年
1、Score-Based Point Cloud Denoising.ICCV 2021.[paper]