English

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

Computer Vision and Pattern Recognition 2021-04-13 v1

Abstract

We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel 2D2^D-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. An iterative transformation refinement module in our network boosts the feature matching accuracy in the intermediate stages. We achieve an inference speed of 12-15ms to register a pair of input point clouds as large as 250K. Extensive evaluation on (i) KITTI LiDAR odometry and (ii) ModelNet-40 datasets shows that our method outperforms prior state-of-the-art methods - e.g., on the KITTI data set, DCP-v2 by1.3 and 1.5 times, and PointNetLK by 1.8 and 1.9 times better rotational and translational accuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is more robust than other benchmark methods when the samples contain a significant amount of noise and other disturbances. RPSRNet accurately registers point clouds with non-uniform sampling densities, e.g., LiDAR data, which cannot be processed by many existing deep-learning-based registration methods.

Keywords

Cite

@article{arxiv.2104.05328,
  title  = {RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation},
  author = {Sk Aziz Ali and Kerem Kahraman and Gerd Reis and Didier Stricker},
  journal= {arXiv preprint arXiv:2104.05328},
  year   = {2021}
}

Comments

Computer Vision and Pattern Recognition (CVPR) 2021, (*Accepted)

R2 v1 2026-06-24T01:04:20.904Z