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

Huibin Li, Haoran Liu, Mingzhe Liu, Yulong Xiao, Peng Li +1 more
12/30/2025
cs.CV

Official code: HaoranLiu507/DehazeSNN (11 stars, MIT, last commit 2026-01-03).

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.

View on arXivView PDF

Code Implementations(1)

HaoranLiu507/DehazeSNNOfficial100%
MIT

DehazeSNN is a lightweight, high-performance image dehazing model that combines a U-Net-like architecture with Spiking Neural Networks. It efficiently captures multi-scale features and handles long-range dependencies, achieving state-of-the-art results with reduced computational cost.

112PythonJun 22, 20259 months agoMIT
image-dehazingspiking-neural-networksu-net

Similar Papers

Haze-Aware Attention Network for Single-Image Dehazing

92% match2024

PriorNet: A Novel Lightweight Network with Multidimensional Interactive Attention for Efficient Image Dehazing

91% match2024

GUSL-Dehaze: A Green U-Shaped Learning Approach to Image Dehazing

90% match2025

RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing

90% match2024

Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining

90% match1 repo12025

Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing

89% match1 repo32024

Cite this paper

@article{li2025unetlike,
  title  = {U-Net-Like Spiking Neural Networks for Single Image Dehazing},
  author = {Huibin Li and Haoran Liu and Mingzhe Liu and Yulong Xiao and Peng Li and Guibin Zan},
  year   = {2025},
  eprint = {2512.23950},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.23950v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.23950.svg)](https://codeofpaper.com/paper/2512.23950)

Discussion