SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
This work addresses rotation sensitivity in point cloud processing, a domain-specific issue for 3D vision applications, with incremental advancements in robustness.
The paper tackles the problem of rotation robustness in 3D point cloud analysis by proposing SPE-Net, which uses selective position encoding to reduce optimization difficulty and improve performance on rotated and unrotated data, achieving evident improvements over state-of-the-art methods on four benchmarks.
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies on an attention mechanism that can effectively attend to the underlying rotation condition of the input. Such encoded rotation condition then determines which part of the network parameters to be focused on, and is shown to efficiently help reduce the degree of freedom of the optimization during training. This mechanism henceforth can better leverage the rotation augmentations through reduced training difficulties, making SPE-Net robust against rotated data both during training and testing. The new findings in our paper also urge us to rethink the relationship between the extracted rotation information and the actual test accuracy. Intriguingly, we reveal evidences that by locally encoding the rotation information through SPE-Net, the rotation-invariant features are still of critical importance in benefiting the test samples without any actual global rotation. We empirically demonstrate the merits of the SPE-Net and the associated hypothesis on four benchmarks, showing evident improvements on both rotated and unrotated test data over SOTA methods. Source code is available at https://github.com/ZhaofanQiu/SPE-Net.