Corpus ID: 236318368

Score-Based Point Cloud Denoising

@article{Luo2021ScoreBasedPC,
  title={Score-Based Point Cloud Denoising},
  author={Shitong Luo and Wei Hu},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.10981}
}
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 noise-free 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 log-likelihood of each point from p ∗ n via gradient ascent—iteratively… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 37 REFERENCES
Differentiable Manifold Reconstruction for Point Cloud Denoising
TLDR
An autoencoder-like neural network is presented, aiming to capture intrinsic structures in point clouds and significantly outperforms state-of-the-art denoising methods under both synthetic noise and real world noise. Expand
PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
TLDR
This work develops a simple data‐driven method for removing outliers and reducing noise in unordered point clouds using a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties in point clouds. Expand
3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation
TLDR
Experimental results show that the proposed NPD algorithm can estimate normal vectors of points in noisy point clouds and achieves better denoising performance and produces much smaller variances. Expand
Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning
TLDR
The results demonstrate unsupervised denoising performance similar to that of supervised learning with clean data when given enough training examples - whereby the student does not need any pairs of noisy and clean training data. Expand
Learning Graph-Convolutional Representations for Point Cloud Denoising
TLDR
A deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by learning-based point cloud processing methods is proposed and significantly outperforms state-of-the-art methods on a variety of metrics. Expand
PU-Net: Point Cloud Upsampling Network
TLDR
A data-driven point cloud upsampling technique to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space, which shows that its upsampled points have better uniformity and are located closer to the underlying surfaces. Expand
Point Cloud Denoising via Moving RPCA
We present an algorithm for the restoration of noisy point cloud data, termed Moving Robust Principal Components Analysis (MRPCA). We model the point cloud as a collection of overlappingExpand
Density-based Denoising of Point Cloud
TLDR
A density-based point cloud denoising method is presented to remove outliers and noisy points and the experimental results show that this approach, comparably, is robust and efficient. Expand
Edge-aware point set resampling
TLDR
The Edge-Aware Resampling algorithm is demonstrated to be capable of producing consolidated point sets with noise-free normals and clean preservation of sharp features, and to lead to improved performance of edge-aware reconstruction methods and point set rendering techniques. Expand
Graph-based denoising for time-varying point clouds
TLDR
This paper introduces a technique that uses this graph structure and convex optimization methods to denoise 3D point clouds and presents how those methods naturally generalize to time-varying inputs such as3D point cloud time series. Expand
...
1
2
3
4
...