Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning
This work addresses the challenge of orientation prediction in 3D point clouds for applications like part segmentation, representing an incremental improvement through a novel hybrid method.
The paper tackles the problem of predicting reliable characteristic orientations for 3D point clouds, which is challenging due to varying appearances, by introducing a method that decouples shape geometry and semantics to achieve stability and consistency, resulting in state-of-the-art performance in point cloud part segmentation with randomly rotated inputs.
Learning to predict reliable characteristic orientations of 3D point clouds is an important yet challenging problem, as different point clouds of the same class may have largely varying appearances. In this work, we introduce a novel method to decouple the shape geometry and semantics of the input point cloud to achieve both stability and consistency. The proposed method integrates shape-geometry-based SO(3)-equivariant learning and shape-semantics-based SO(3)-invariant residual learning, where a final characteristic orientation is obtained by calibrating an SO(3)-equivariant orientation hypothesis using an SO(3)-invariant residual rotation. In experiments, the proposed method not only demonstrates superior stability and consistency but also exhibits state-of-the-art performances when applied to point cloud part segmentation, given randomly rotated inputs.