U-Net-Like Spiking Neural Networks for Single Image Dehazing

TL;DR

This paper introduces DehazeSNN, a novel U-Net-like spiking neural network architecture that effectively performs single image dehazing with reduced computational costs and improved performance over existing deep learning methods.

Contribution

The paper presents a new SNN-based architecture with OLIFBlock for efficient multi-scale feature extraction in image dehazing, outperforming traditional CNN and Transformer approaches.

Findings

DehazeSNN achieves competitive results on benchmark datasets.

The model has a smaller size and fewer multiply-accumulate operations.

It delivers high-quality haze removal with lower computational resources.

Abstract

Image dehazing is a critical challenge in computer vision, essential for enhancing image clarity in hazy conditions. Traditional methods often rely on atmospheric scattering models, while recent deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Transformers, have improved performance by effectively analyzing image features. However, CNNs struggle with long-range dependencies, and Transformers demand significant computational resources. To address these limitations, we propose DehazeSNN, an innovative architecture that integrates a U-Net-like design with Spiking Neural Networks (SNNs). DehazeSNN captures multi-scale image features while efficiently managing local and long-range dependencies. The introduction of the Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) enhances cross-channel communication, resulting in superior dehazing performance with reduced computational burden. Our extensive experiments show that DehazeSNN is highly competitive to state-of-the-art methods on benchmark datasets, delivering high-quality haze-free images with a smaller model size and less multiply-accumulate operations. The proposed dehazing method is publicly available at https://github.com/HaoranLiu507/DehazeSNN.