NSANet: Noise Seeking Attention Network

TL;DR

NSANet is a novel neural network designed to effectively filter atmospheric noise in high-density LiDAR point clouds, leveraging physical priors and attention mechanisms to improve scene quality.

Contribution

The paper introduces NSANet, a dual-attention neural network that incorporates physical priors and local spatial attention for noise filtering in LiDAR data, inspired by psychology theories.

Findings

NSANet outperforms existing noise-filtering neural networks.

Attention mechanisms improve noise suppression in LiDAR point clouds.

Results support the role of attention engagement theory in computer vision.

Abstract

LiDAR (Light Detection and Ranging) technology has remained popular in capturing natural and built environments for numerous applications. The recent technological advancements in electro-optical engineering have aided in obtaining laser returns at a higher pulse repetition frequency (PRF), which considerably increased the density of the 3D point cloud. Conventional techniques with lower PRF had a single pulse-in-air (SPIA) zone, large enough to avoid a mismatch among pulse pairs at the receiver. New multiple pulses-in-air (MPIA) technology guarantees various windows of operational ranges for a single flight line and no blind zones. The disadvantage of the technology is the projection of atmospheric returns closer to the same pulse-in-air zone of adjacent terrain points likely to intersect with objects of interest. These noise properties compromise the perceived quality of the scene and encourage the development of new noise-filtering neural networks, as existing filters are significantly ineffective. We propose a novel dual-attention noise-filtering neural network called Noise Seeking Attention Network (NSANet) that uses physical priors and local spatial attention to filter noise. Our research is motivated by two psychology theories of feature integration and attention engagement to prove the role of attention in computer vision at the encoding and decoding phase. The presented results of NSANet show the inclination towards attention engagement theory and a performance boost compared to the state-of-the-art noise-filtering deep convolutional neural networks.