Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning
@article{Hermosilla2019TotalDU, title={Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning}, author={P. Hermosilla and T. Ritschel and T. Ropinski}, journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)}, year={2019}, pages={52-60} }
We show that denoising of 3D point clouds can be learned unsupervised, directly from noisy 3D point cloud data only. [...] Key Method Overcoming this, we introduce a spatial prior term, that steers converges to the unique closest out of the many possible modes on a manifold. Our results demonstrate unsupervised denoising performance similar to that of supervised learning with clean data when given enough training examples - whereby we do not need any pairs of noisy and clean training data.Expand Abstract
Figures, Tables, and Topics from this paper
12 Citations
Differentiable Manifold Reconstruction for Point Cloud Denoising
- Computer Science
- ACM Multimedia
- 2020
- 3
- Highly Influenced
- PDF
Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance.
- Computer Science, Engineering
- 2020
- PDF
Learning Graph-Convolutional Representations for Point Cloud Denoising
- Computer Science, Engineering
- ECCV
- 2020
- PDF
PointAugment: An Auto-Augmentation Framework for Point Cloud Classification
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 8
- PDF
Differentiable surface splatting for point-based geometry processing
- Computer Science
- ACM Trans. Graph.
- 2019
- 24
- PDF
References
SHOWING 1-10 OF 40 REFERENCES
PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
- Computer Science
- Comput. Graph. Forum
- 2020
- 36
- Highly Influential
- PDF
PointProNets: Consolidation of Point Clouds with Convolutional Neural Networks
- Computer Science
- Comput. Graph. Forum
- 2018
- 24
PCPNet Learning Local Shape Properties from Raw Point Clouds
- Computer Science, Mathematics
- Comput. Graph. Forum
- 2018
- 113
- PDF
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 3,375
- Highly Influential
- PDF
A Point Set Generation Network for 3D Object Reconstruction from a Single Image
- Computer Science, Mathematics
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 727
- PDF
Monte Carlo convolution for learning on non-uniformly sampled point clouds
- Computer Science
- ACM Trans. Graph.
- 2018
- 91
- PDF
Patch‐Collaborative Spectral Point‐Cloud Denoising
- Mathematics, Computer Science
- Comput. Graph. Forum
- 2013
- 37
- PDF