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. Code available at https://code.active.vision.
@article{arxiv.2008.09965,
title = {Neighbourhood-Insensitive Point Cloud Normal Estimation Network},
author = {Zirui Wang and Victor Adrian Prisacariu},
journal= {arXiv preprint arXiv:2008.09965},
year = {2021}
}
Comments
Accepted in BMVC 2020 as oral presentation. Code available at https://code.active.vision and project page at http://ninormal.active.vision