Transformation-Equivariant 3D Object Detection for Autonomous Driving. (arXiv:2211.11962v2 [cs.CV] UPDATED)

3D object detection received increasing attention in autonomous driving
recently. Objects in 3D scenes are distributed with diverse orientations.
Ordinary detectors do not explicitly model the variations of rotation and
reflection transformations. Consequently, large networks and extensive data
augmentation are required for robust detection. Recent equivariant networks
explicitly model the transformation variations by applying shared networks on
multiple transformed point clouds, showing great potential in object geometry
modeling. However, it is difficult to apply such networks to 3D object
detection …

arxiv autonomous autonomous driving detection driving transformation