
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Luo_2021_ICCV, author = {Luo, Shitong and Hu, Wei}, title = {ScoreBased Point Cloud Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {45834592} }
ScoreBased Point Cloud Denoising
Abstract
Point clouds acquired from scanning devices are often perturbed by noise, which affects downstream tasks such as surface reconstruction and analysis. The distribution of a noisy point cloud can be viewed as the distribution of a set of noisefree samples p(x) convolved with some noise model n, leading to (p * n)(x) whose mode is the underlying clean surface. To denoise a noisy point cloud, we propose to increase the loglikelihood of each point from p * n via gradient ascentiteratively updating each point's position. Since p * n is unknown at testtime, and we only need the score (i.e., the gradient of the logprobability function) to perform gradient ascent, we propose a neural network architecture to estimate the score of p * n given only noisy point clouds as input. We derive objective functions for training the network and develop a denoising algorithm leveraging on the estimated scores. Experiments demonstrate that the proposed model outperforms stateoftheart methods under a variety of noise models, and shows the potential to be applied in other tasks such as point cloud upsampling.
Related Material