#### PointCleanNet: Learning to Denoise and Remove Outliersfrom Dense Point Clouds

• Marie-Julie Rakotosaona*1
• Vittorio La Barbera*2
• Paul Guerrero 2
• Niloy J. Mitra 2,3
• Maks Ovsjanikov 1

1LIX, École Polytechnique, CNRS         2University College London         3Adobe Research
*joint first authors

Computer Graphics Forum 2019

We present PointCleanNet, a two-stage network that takes a raw point cloud (left) and first removes outliers (middle) and then denoises the remaining pointset (right). Our method, unlike many traditional approaches, is parameter-free and automatically discovers and preserves high-curvature features without requiring additional information about the underlying surface type or device characteristics. Here, point clouds are colored based on error compared to the ground truth point cloud (blue denoting low error, red denoting high error).

###### Abstract

Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g., jets or MLS surfaces), local or non-local averaging, or on statistical assumptions about the underlying noise model. In contrast, we develop a simple data-driven method for removing outliers and reducing noise in unordered point clouds. We base our approach on a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties in point clouds. Our method first classifies and discards outlier samples, and then estimates correction vectors that project noisy points onto the original clean surfaces. The approach is efficient and robust to varying amounts of noise and outliers, while being able to handle large densely-sampled point clouds. In our extensive evaluation, both on synthesic and real data, we show an increased robustness to strong noise levels compared to various state-of-the-art methods, enabling accurate surface reconstruction from extremely noisy real data obtained by range scans. Finally, the simplicity and universality of our approach makes it very easy to integrate in any existing geometry processing pipeline.

###### Bibtex
@ARTICLE{RakotosaonaEtAl:PointCleanNet:CGF:2019,
author = {Marie-Julie Rakotosaona and Vittorio La Barbera and Paul Guerrero and Niloy {J. Mitra} and Maks Ovsjanikov},
title = {{PointCleanNet}: Learning to Denoise and Remove Outliers from Dense Point Clouds},
journal = {{Computer Graphics Forum}},
year = 2019
}

###### Acknowledgements

Parts of this work were supported by the KAUST OSR Award No. CRG-2017-3426, a gift from the NVIDIA Corporation, the ERC Starting Grants EXPROTEA (StG-2017-758800) and SmartGeometry (StG-2013-335373), a Google Faculty Award, and gifts from Adobe.