Multi-Dimensional Graph Interactional Network for Progressive Point Cloud Completion
- 9 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Abstract
Point cloud completion refers to inferring the complete and visually plausible shape from a partial input. Existing point cloud completion methods focus on recovering the global integrity of partial point clouds but lack local structural details. Furthermore, they seldom consider the shape faithfulness of completed results, that some completed points fail to fall into the ground truth position faithfully. To meet the above challenges, we present a multi-dimensional graph interactional network for progressive point cloud completion. Specifically, we propose a multi-resolution multi-dimensional graph encoder (MRMD-GE) to capture the information from both within-dimension and cross-dimension interactions for the purpose of enhancing the perception of local geometry. Inspired by the FPN, we develop a recursive point cloud pyramid decoder (RPPD) for generating multi-stage completed point clouds progressively, which incorporates extra feedback connections into the bottom-up backbone layers. In addition, we design a depth map discriminator combined with differentiable rendering to match the distribution of generated and real point clouds, making the completed point clouds more faithful to the ground truth. Quantitative and qualitative experiments on Completion3D, Shapenet-Part and KITTI datasets demonstrate that our proposed method has compelling advantages over the state-of-the-art methods.Keywords
Funding Information
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (2018024)
- National Natural Science Foundation of China (61976095, 61575209)
- Experiments for Space Exploration Program and the Qian Xuesen Laboratory, China Academy of Space Technology (TKTSPY-2020-05-01)
This publication has 52 references indexed in Scilit:
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Context Encoders: Feature Learning by Inpainting2016
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Database‐Assisted Object Retrieval for Real‐Time 3D ReconstructionComputer Graphics Forum, 2015
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Screened poisson surface reconstructionACM Transactions on Graphics, 2013
- Discovering structural regularity in 3D geometry2008
- Articulated Object Reconstruction and Markerless Motion Capture from Depth VideoComputer Graphics Forum, 2008