Neighbourhood-Insensitive Point Cloud Normal Estimation Network (BMVC 2020 Oral)

BMVC 2020

Details
Code: https://github.com/ActiveVisionLab/NINormal Project: http://ninormal.active.vision/ Paper: http://www.robots.ox.ac.uk/~ryan/bmvc2020/0028.pdf Supp: http://www.robots.ox.ac.uk/~ryan/bmvc2020/0028_supp.pdf Abstract: We introduce a novel self-attention-based normal estimation network that is able to focus softly on relevant points and adjust the softness by learning a temperature parameter, making it able to work naturally and effectively within a large neighbourhood range. As a result, our model outperforms all existing normal estimation algorithms by a large margin, achieving 94.1% accuracy in comparison with the previous state of the art of 91.2%, with a 25x smaller model and 12x faster inference time. We also use point-to-plane Iterative Closest Point (ICP) as an application case to show that our normal estimations lead to faster convergence than normal estimations from other methods, without manually fine-tuning neighbourhood range parameters.

Comments
loading...