PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds

By Marie-Julie Rakotosaona, Vittorio La Barbera, Paul Guerrero, Niloy J. Mitra, M. Ovsjanikov. Computer graphics forum (Print), 2019

406 citations recorded by the source corpus.

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 synthetic 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. Both the code and pre‐trained networks can be found on the project page (https://github.com/mrakotosaon/pointcleannet).

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/776ac1c3003e162e662b21c3a5c189b5e449c03f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Olga Sorkine-Hornung
2. Yifan Wang
3. Felice Serena
4. Chaoda Zheng
5. Shuguang Cui
6. Xu Yan
7. Cengiz Öztireli
8. Sheng Wang

In Computer Vision and Pattern Recognition

1. Olga Sorkine-Hornung
2. Felice Serena
3. Chaoda Zheng
4. Shuguang Cui
5. Xu Yan
6. Yifan Wang
7. Cengiz Öztireli
8. Sheng Wang

In Geology

1. Chaoda Zheng
2. Shuguang Cui
3. Xu Yan
4. Sheng Wang
5. Zhuguo Li

Citations in the corpus

• PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling (2020, methodology): “Various data-driven methods [9, 26] are proposed for outlier removal, which first discard some outliers and then projects noisy points to clean surfaces.”
• Differentiable surface splatting for point-based geometry processing (2019, methodology): “Based on PointNet [Qi et al. 2017a], PCPNET [Guerrero et al. 2018] and PointCleanNet [Rakotosaona et al. 2019] 2014] and NMR [Kato et al. 2018] do not propagate gradients to depth; Paparazzi [Liu et al. 2018] has limitation in updating the vertex positions in directions orthogonal their face normals”