Point Cloud Completion by Skip-attention Network with Hierarchical Folding
Preprint
Abstract
Point cloud completion aims to infer the complete geometries for missing regions of 3D objects from incomplete ones. Previous methods usually predict the complete point cloud based on the global shape representation extracted from the incomplete input. However, the global representation often suffers from the information loss of structure details on local regions of incomplete point cloud. To address this problem, we propose Skip-Attention Network (SA-Net) for 3D point cloud completion. Our main contributions lie in the following two-folds. First, we propose a skip-attention mechanism to effectively exploit the local structure details of incomplete point clouds during the inference of missing parts. The skip-attention mechanism selectively conveys geometric information from the local regions of incomplete point clouds for the generation of complete ones at different resolutions, where the skip-attention reveals the completion process in an interpretable way. Second, in order to fully utilize the selected geometric information encoded by skip-attention mechanism at different resolutions, we propose a novel structure-preserving decoder with hierarchical folding for complete shape generation. The hierarchical folding preserves the structure of complete point cloud generated in upper layer by progressively detailing the local regions, using the skip-attentioned geometry at the same resolution. We conduct comprehensive experiments on ShapeNet and KITTI datasets, which demonstrate that the proposed SA-Net outperforms the state-of-the-art point cloud completion methods.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud InpaintingIEEE Transactions on Image Processing, 2019
- 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention AggregationIEEE Transactions on Image Processing, 2019
- SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With AttentionIEEE Transactions on Image Processing, 2018
- Deep Spatiality: Unsupervised Learning of Spatially-Enhanced Global and Local 3D Features by Deep Neural Network With Coupled SoftmaxIEEE Transactions on Image Processing, 2018
- Unsupervised Learning of 3-D Local Features From Raw Voxels Based on a Novel Permutation Voxelization StrategyIEEE Transactions on Cybernetics, 2017
- BoSCC: Bag of Spatial Context Correlations for Spatially Enhanced 3D Shape RepresentationIEEE Transactions on Image Processing, 2017
- Unsupervised 3D Local Feature Learning by Circle Convolutional Restricted Boltzmann MachineIEEE Transactions on Image Processing, 2016
- Mesh Convolutional Restricted Boltzmann Machines for Unsupervised Learning of Features With Structure Preservation on 3-D MeshesIEEE Transactions on Neural Networks and Learning Systems, 2016
- A query expansion method for retrieving online BIM resources based on Industry Foundation ClassesAutomation in Construction, 2015
- Computing the Inner Distances of Volumetric Models for Articulated Shape Description with a Visibility GraphIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011