Spiking neural network improves remote sensing image dehazing with low energy
EM-SNN: Efficiently Modulated Spiking Neural Network for Remote Sensing Image Dehazing
Computer Vision and Pattern Recognition
Summary
Hazy images from remote sensing make it hard to see details clearly. The authors designed a special type of spiking neural network that processes images efficiently and restores those lost details better by adapting to the haze’s effects. Their model uses a new neuron type and a method to highlight edges while keeping energy use low. Tests showed this approach cleans up images as well as other methods but uses much less power.
What this means in practice
- •For remote sensing engineers: Enhance clarity of satellite and aerial images affected by haze using energy-efficient neural network models.
- •For embedded vision system developers: Integrate low-power spiking neural networks to improve real-time dehazing in resource-constrained imaging devices.
Authors
Jie Shao, Jiaqi Ma, Wenwen Min, Beihang Song, Ning Chen, Youfa Liu, Jun Wan
Abstract
Although spiking neural networks (SNNs) provide an energy-efficient alternative to artificial neural networks (ANNs), their application to remote sensing image dehazing remains limited. A key challenge arises from the coupling between haze-induced high-frequency attenuation and discrete spike thresholding. This interaction suppresses weak responses and fundamentally limits the recovery of edges, textures, and fine details in spiking dehazing models. To address this challenge, we propose the Efficiently Modulated Spiking Neural Network (EM-SNN), a dedicated spiking framework tailored to remote sensing image dehazing. EM-SNN integrates a statistics-driven Threshold-Modulated Leaky Integrate-and-Fire (TM-LIF) neuron to adaptively compensate for haze-induced contrast compression, together with a Spike Sobel Modulation (SSM) module that enhances structural cues and reduces depth-wise attenuation during spiking feature propagation. By jointly modulating activation scales and structural representations, EM-SNN improves dehazing performance while preserving the inherent event-driven sparsity of SNNs. Experiments on HRSD, RICE, RRSHID, and SateHaze1K demonstrate that EM-SNN achieves competitive dehazing performance while consuming only one quarter of the energy of the strong ANN baseline SFRDP-Net.