Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning

  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)},
  • P. Hermosilla, T. Ritschel, T. Ropinski
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 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
    10 Citations
    Differentiable Manifold Reconstruction for Point Cloud Denoising
    • 2
    • Highly Influenced
    • PDF
    Learning Graph-Convolutional Representations for Point Cloud Denoising
    Non-Local Part-Aware Point Cloud Denoising
    Deep Learning for 3D Point Cloud Understanding: A Survey
    Finding Your (3D) Center: 3D Object Detection Using a Learned Loss
    PointAugment: An Auto-Augmentation Framework for Point Cloud Classification
    • 5
    • PDF
    Differentiable surface splatting for point-based geometry processing
    • 22
    • PDF
    Joint Learning of Blind Video Denoising and Optical Flow Estimation


    PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
    • 33
    • Highly Influential
    • PDF
    PointProNets: Consolidation of Point Clouds with Convolutional Neural Networks
    • 24
    PCPNet Learning Local Shape Properties from Raw Point Clouds
    • 101
    • PDF
    The Bilateral Filter for Point Clouds
    • 16
    • PDF
    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    • 3,047
    • Highly Influential
    • PDF
    EC-Net: an Edge-aware Point set Consolidation Network
    • 50
    • PDF
    A Point Set Generation Network for 3D Object Reconstruction from a Single Image
    • Haoqiang Fan, H. Su, L. Guibas
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 672
    • PDF
    Monte Carlo convolution for learning on non-uniformly sampled point clouds
    • 77
    • PDF
    Patch‐Collaborative Spectral Point‐Cloud Denoising
    • 36
    • PDF
    ℓ1-Sparse reconstruction of sharp point set surfaces
    • 128
    • PDF