Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling

  title={Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling},
  author={Dongbo Zhang and Xuequan Lu and Hong Qin and Ying He},
  journal={IEEE Transactions on Visualization and Computer Graphics},
Point cloud filtering is a fundamental problem in geometry modeling and processing. Despite of significant advancement in recent years, the existing methods still suffer from two issues: 1) they are either designed without preserving sharp features or less robust in feature preservation; and 2) they usually have many parameters and require tedious parameter tuning. In this article, we propose a novel deep learning approach that automatically and robustly filters point clouds by removing noise… 
Deep Feature-preserving Normal Estimation for Point Cloud Filtering
AGConv: Adaptive Graph Convolution on 3D Point Clouds
AGConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts, and implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points.
Point cloud denoising review: from classical to deep learning-based approaches
This article provides a comprehensive survey on state-of-the-art denoising solutions, which are mainly categorized into three classes: filter-based, optimization- based, and deep learning- based techniques.
Towards Uniform Point Distribution in Feature-preserving Point Cloud Filtering
This paper introduces a point cloud filtering method that considers both point distribution and feature preservation during filtering, and incorporates a repulsion term with a data term in energy minimization.
Deep Point Cloud Normal Estimation via Triplet Learning
Despite having a smaller network size compared to most other methods, experimental results show that the proposed normal estimation method preserves sharp features and achieves better normal estimation results on CAD-like shapes.
GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation
This work proposes to learn graph convolutional feature representation for normal estimation, which emphasizes more local neighborhood geometry and effectively encodes intrinsic relationships and is quite robust against noise, outliers, as well as the density variations.
Out-of-core outlier removal for large-scale indoor point clouds
Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators
Complete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators, are presented and the relation of the classical localized L 1 estimator, used in the LOP operator for surface reconstruction from noisy point clouds, is revealed via a novel kernel.


PointProNets: Consolidation of Point Clouds with Convolutional Neural Networks
This work proposes a generative neural network architecture that can input and output point clouds, unlocking a powerful set of tools from the deep learning literature and uses this architecture to apply convolutional neural networks to local patches of geometry for high quality and efficient point cloud consolidation.
PU-Net: Point Cloud Upsampling Network
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.
PCPNet Learning Local Shape Properties from Raw Point Clouds
The utility of the PCPNET approach in the context of shape reconstruction is demonstrated, by showing how it can be used to extract normal orientation information from point clouds.
Guided point cloud denoising via sharp feature skeletons
A variety of experiments suggest that the key idea to address the issue is to assign feature points with multiple normals according to their feature type, and can robustly filter out high level of noise while keeping the important geometric features intact.
GPF: GMM-Inspired Feature-Preserving Point Set Filtering
This paper proposes a novel approach for robust feature-preserving point set filtering, inspired by the Gaussian Mixture Model (GMM), which can robustly reconstruct a high-quality point set which is both noise-free and feature- Preserving.
Dynamic Graph CNN for Learning on Point Clouds
This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
This work proposes a novel convolutional architecture, termed SpiderCNN, to efficiently extract geometric features from point clouds, which inherits the multi-scale hierarchical architecture from the classical CNNs, which allows it to extract semantic deep features.
PRIN: Pointwise Rotation-Invariant Network
This paper proposes a new point-set learning framework named Pointwise Rotation-Invariant Network (PRIN), focusing on achieving rotation-invariance in point clouds, and shows performance better than state-of-the-art methods on part segmentation without data augmentation.
Computer Vision and Pattern Recognition (CVPR)
PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
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.