Name
Abstract | ||
|---|---|---|
The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedforward, and high-level information is rarely reused to improve low-level feature learning. To this end, we propose a novel Feedback Network (FBNet) for point cloud completion, in which present features are efficiently refined by rerouting subsequent fine-grained ones. Firstly, partial inputs are fed to a Hierarchical Graph-based Network (HGNet) to generate coarse shapes. Then, we cascade several Feedback-Aware Completion (FBAC) Blocks and unfold them across time recurrently. Feedback connections between two adjacent time steps exploit fine-grained features to improve present shape generations. The main challenge of building feedback connections is the dimension mismatching between present and subsequent features. To address this, the elaborately designed point Cross Transformer exploits efficient information from feedback features via cross attention strategy and then refines present features with the enhanced feedback features. Quantitative and qualitative experiments on several datasets demonstrate the superiority of proposed FBNet compared to state-of-the-art methods on point completion task. The source code and model are available at https://github.com/hikvision-research/3DVision/. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1007/978-3-031-20086-1_39 | European Conference on Computer Vision |
Keywords | DocType | Citations |
Point cloud completion,Feedback network,Cross transformer | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xuejun Yan | 1 | 0 | 0.34 |
| Hongyu Yan | 2 | 0 | 0.34 |
| Jingjing Wang | 3 | 0 | 0.34 |
| Hang Du | 4 | 0 | 0.34 |
| Zhihong Wu | 5 | 0 | 0.34 |
| Di Xie | 6 | 0 | 0.34 |
| Shiliang Pu | 7 | 187 | 42.65 |
| Li Lu | 8 | 0 | 0.34 |