Title | ||
---|---|---|
L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention |
Abstract | ||
---|---|---|
Auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learning of global structure by global shape reconstruction, while ignoring the learning of local structures. To resolve this issue, we propose Local-to-Global auto-encoder (L2G-AE) to simultaneously learn the local and global structure of point clouds by local to global reconstruction. Specifically, L2G-AE employs an encoder to encode the geometry information of multiple scales in a local region at the same time. In addition, we introduce a novel hierarchical self-attention mechanism to highlight the important points, scales and regions at different levels in the information aggregation of the encoder. Simultaneously, L2G-AE employs a recurrent neural network (RNN) as decoder to reconstruct a sequence of scales in a local region, based on which the global point cloud is incrementally reconstructed. Our outperforming results in shape classification, retrieval and upsampling show that L2G-AE can understand point clouds better than state-of-the-art methods.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3343031.3350960 | Proceedings of the 27th ACM International Conference on Multimedia |
Keywords | DocType | ISBN |
auto-encoder, hierarchical attention, interpolation layer, point cloud, recurrent neural network, unsupervised learning | Conference | 978-1-4503-6889-6 |
Citations | PageRank | References |
8 | 0.47 | 26 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xinhai Liu | 1 | 32 | 2.17 |
Han Zhizhong | 2 | 198 | 18.28 |
Xin Wen | 3 | 24 | 2.71 |
Yu-shen Liu | 4 | 319 | 23.20 |
Zwicker Matthias | 5 | 2513 | 129.25 |