Geometry Sharing Network for 3D Point Cloud Classification and Segmentation
| Autor: | Zhipeng Zhou, Yu Qiao, Mingye Xu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Similarity (geometry) Euclidean space Computer science Computer Vision and Pattern Recognition (cs.CV) Point cloud Computer Science - Computer Vision and Pattern Recognition Geometry 02 engineering and technology General Medicine 021001 nanoscience & nanotechnology Curvature Convexity Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation 0210 nano-technology Eigenvalues and eigenvectors Transformation geometry |
| Zdroj: | AAAI |
| Popis: | In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we propose Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations. Compared with previous 3D point CNNs which perform convolution on nearby points, GS-Net can aggregate point features in a more global way. Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space. This design allows GS-Net to efficiently capture both local and holistic geometric features such as symmetry, curvature, convexity and connectivity. Theoretically, we show the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet Part. Experiments demonstrate that GS-Net achieves the state-of-the-art performances on major datasets, 93.3% on ModelNet40, and are more robust to geometric transformations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|