Neighbourhood-Insensitive Point Cloud Normal Estimation Network
This work addresses the challenge of accurate and efficient normal estimation in point clouds for applications like 3D reconstruction, offering significant improvements over existing methods.
The paper tackles the problem of point cloud normal estimation by introducing a self-attention-based network that adaptively focuses on relevant points, achieving 94.1% accuracy compared to the previous state-of-the-art of 91.2%, with a 25x smaller model and 12x faster inference time.
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.