English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose RPSRNet - a novel end-to-end trainable deep neural network forrigid point set registration. For this task, we use a novel $2^D$-treerepresentation for the input point sets and a hierarchical deep featureembedding in the neural network. An iterative transformation refinement modulein 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 pointclouds as large as 250K. Extensive evaluation on (i) KITTI LiDAR odometry and(ii) ModelNet-40 datasets shows that our method outperforms priorstate-of-the-art methods - e.g., on the KITTI data set, DCP-v2 by1.3 and 1.5times, and PointNetLK by 1.8 and 1.9 times better rotational and translationalaccuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is morerobust than other benchmark methods when the samples contain a significantamount of noise and other disturbances. RPSRNet accurately registers pointclouds with non-uniform sampling densities, e.g., LiDAR data, which cannot beprocessed by many existing deep-learning-based registration methods.

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