CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
@article{Xu2022CPNetCR, title={CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning}, author={Mingye Xu and Zhipeng Zhou and Hongbin Xu and Yali Wang and Yu Qiao}, journal={ArXiv}, year={2022}, volume={abs/2201.08215} }
—Self-supervised learning has not been fully explored for point cloud analysis. Current frameworks are mainly based on point cloud reconstruction. Given only 3D coordinates, such approaches tend to learn local geometric structures and contours, while failing in understanding high level semantic content. Consequently, they achieve unsatisfactory performance in downstream tasks such as classification, segmentation, etc. To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network…
Figures and Tables from this paper
References
SHOWING 1-10 OF 53 REFERENCES
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
- Computer Science2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
A novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds, and is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid.
Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
- Computer ScienceACM Multimedia
- 2021
A novel self-contrastive learning for self-supervised point cloud representation learning, aiming to capture both local geometric patterns and nonlocal semantic primitives based on the nonlocal self-similarity of point clouds.
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
- Computer Science2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2019
RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis, achieves the state of the arts and a hierarchical architecture can be developed to achieve contextual shape-aware learning for Point cloud analysis.
Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
- Computer Science2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
The outperforming results in four shape analysis tasks show that MAP-VAE can learn more discriminative global or local features than the state-of-the-art methods.
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
- Computer ScienceAAAI
- 2021
GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components, and exploits Sharp-Gentle Complementary Attention Module that regards the features from sharp and Gentle variation components as two holistic representations.
Dynamic Graph CNN for Learning on Point Clouds
- Computer Science, Environmental ScienceACM Trans. Graph.
- 2019
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.
Shape Self-Correction for Unsupervised Point Cloud Understanding
- Computer Science2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2021
A novel self-supervised learning method named Shape Self-Correction for point cloud analysis that achieves state-of-the-art performance among unsupervised methods and it is shown experimentally that pre-training with the framework significantly boosts the performance of supervised models.
Geometry Sharing Network for 3D Point Cloud Classification and Segmentation
- Computer ScienceAAAI
- 2020
This work proposes Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations and shows the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation.
PointWise: An Unsupervised Point-wise Feature Learning Network
- Computer ScienceArXiv
- 2019
A deep learning framework to learn point-wise description from a set of shapes without supervision that leverages self-supervision to define a relevant loss function to learn rich per-point features and demonstrates the ability of the method to capture meaningful point- Wise features through three applications.
L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
- Computer ScienceACM Multimedia
- 2019
Local-to-Global auto-encoder (L2G-AE) is proposed to simultaneously learn the local and global structure of point clouds by local to global reconstruction to understand point clouds better than state-of-the-art methods.