Recently, significant progress has been achieved in analyzing the 3D point cloud with deep learning techniques. However, existing networks suffer from poor generalization and robustness to arbitrary rotations applied to the input point cloud. Different from traditional strategies that improve the rotation robustness with data augmentation or specifically designed spherical representation or harmonics-based kernels, we propose to rotate the point cloud into a canonical viewpoint for boosting the following downstream target task, e.g., object classification and part segmentation. Specifically, the canonical viewpoint is predicted by the network RotPredictor in an unsupervised way and the loss function is only built on the target task. Our RotPredictor satisfies the rotation equivariance property in (3) approximately and the predication output has the linear relationship with the applied rotation transformation. In addition, the RotPredictor is an independent plug and play module, which can be employed by any point-based deep learning framework without extra burden. Experimental results on the public model classification dataset ModelNet40 show the performance for all baselines can be boosted by integrating the proposed module. In addition, by adding our proposed module, we can achieve the state-of-the-art classification accuracy with 90.2% on the rotation-augmented ModelNet40 benchmark.
|Title of host publication||Proceedings - 2020 International Conference on 3D Vision, 3DV 2020|
|Number of pages||10|
|State||Published - Nov 2020|
|Event||8th International Conference on 3D Vision, 3DV 2020 - Virtual, Fukuoka, Japan|
Duration: Nov 25 2020 → Nov 28 2020
|Name||Proceedings - 2020 International Conference on 3D Vision, 3DV 2020|
|Conference||8th International Conference on 3D Vision, 3DV 2020|
|Period||11/25/20 → 11/28/20|
Bibliographical notePublisher Copyright:
© 2020 IEEE.
- point cloud classification
- rotation equivariance
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Vision and Pattern Recognition