Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
10-2024
Abstract
Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several recent studies achieve rotation invariance at the cost of lower accuracies. In this work, we close this gap by proposing a novel yet effective rotation invariant architecture for 3D point cloud classification and segmentation. Instead of traditional pointwise operations, we construct local triangle surfaces to capture more detailed surface structure, based on which we can extract highly expressive rotation invariant surface properties which are then integrated into an attention-augmented convolution operator named RISurConv to generate refined attention features via self-attention layers. Based on RISurConv we build an effective neural network for 3D point cloud analysis that is invariant to arbitrary rotations while maintaining high accuracy. We verify the performance on various benchmarks with supreme results obtained surpassing the previous state-of-the-art by a large margin. We achieve an overall accuracy of 96.0{\%} (+4.7{\%}) on ModelNet40, 93.1{\%} (+12.8{\%}) on ScanObjectNN, and class accuracies of 91.5{\%} (+3.6{\%}), 82.7{\%} (+5.1{\%}), and 78.5{\%} (+9.2{\%}) on the three categories of the FG3D dataset for the fine-grained classification task. Additionally, we achieve 81.5{\%} (+1.0{\%}) mIoU on ShapeNet for the segmentation task.
Keywords
Point cloud, Rotation invariant, Attention, Deep learning
Discipline
Artificial Intelligence and Robotics | Computer Sciences
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 18th European Conference on Computer Vision (ECCV 2024) : Milan, Italy, September 29 - October 4
First Page
93
Last Page
109
ISBN
9783031733895
Identifier
10.1007/978-3-031-73390-1_6
Publisher
Springer Nature
City or Country
Cham
Citation
ZHANG, Zhiyuan; YANG, Licheng; and XIANG Zhiyu.
RISurConv : Rotation invariant surface attention-augmented convolutions for 3D point cloud classification and segmentation. (2024). Proceedings of the 18th European Conference on Computer Vision (ECCV 2024) : Milan, Italy, September 29 - October 4. 93-109.
Available at: https://ink.library.smu.edu.sg/sis_research/9747
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/978-3-031-73390-1_6
Comments
ECCV 2024 Oral. PDF provided by faculty