Partial-to-Partial Point Generation Network for Point Cloud Completion
- 28 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 11990-11997
Abstract
Point cloud completion aims at predicting dense complete 3D shapes from sparse incomplete point clouds captured from 3D sensors or scanners. It plays an essential role in various applications such as autonomous driving, 3D reconstruction, augmented reality, and robot navigation. Existing point cloud completion methods follow the encoder-decoder paradigm, in which the complete point clouds are recovered in a coarse-to-fine strategy. However, only using the global feature is difficult and will lead to blurring of the global structure and distortion of local details. To address this problem, we propose a novel Partial-to-Partial Point Generation Network ( $\text{P}^{2}$ GNet), a learning-based approach for point cloud completion. In $\text{P}^{2}$ GNet, we use a feature disentangle encoder to obtain the global feature, and missing code and novel view partial point cloud are generated conditioned on the view-related missing code. To better aggregate partial point clouds, an attentive sampling module is proposed to sample multiple partial point clouds into the final complete result. Extensive experiments on several public benchmarks demonstrate that our $\text{P}^{2}$ GNet outperforms state-of-the-art point cloud completion methods.Keywords
Funding Information
- Frontier Leading Technology of Jiangsu Province of China (BK20192004C)
This publication has 40 references indexed in Scilit:
- PCN: Point Completion Network2018
- A novel dual-camera calibration method for 3D optical measurementOptics and Lasers in Engineering, 2018
- Shape completion enabled robotic grasping2017
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis2017
- A Field Model for Repairing 3D Shapes2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Data-driven structural priors for shape completionACM Transactions on Graphics, 2015
- LSD-SLAM: Large-Scale Direct Monocular SLAM2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013