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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Jain, Akshat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913725576904704
author Jain, Akshat
author_facet Jain, Akshat
contents This paper presents a novel approach to image dehazing by combining Feature Fusion Attention (FFA) networks with CycleGAN architecture. Our method leverages both supervised and unsupervised learning techniques to effectively remove haze from images while preserving crucial image details. The proposed hybrid architecture demonstrates significant improvements in image quality metrics, achieving superior PSNR and SSIM scores compared to traditional dehazing methods. Through extensive experimentation on the RESIDE and DenseHaze CVPR 2019 dataset, we show that our approach effectively handles both synthetic and real-world hazy images. CycleGAN handles the unpaired nature of hazy and clean images effectively, enabling the model to learn mappings even without paired data.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06107
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining
Jain, Akshat
Computer Vision and Pattern Recognition
Artificial Intelligence
This paper presents a novel approach to image dehazing by combining Feature Fusion Attention (FFA) networks with CycleGAN architecture. Our method leverages both supervised and unsupervised learning techniques to effectively remove haze from images while preserving crucial image details. The proposed hybrid architecture demonstrates significant improvements in image quality metrics, achieving superior PSNR and SSIM scores compared to traditional dehazing methods. Through extensive experimentation on the RESIDE and DenseHaze CVPR 2019 dataset, we show that our approach effectively handles both synthetic and real-world hazy images. CycleGAN handles the unpaired nature of hazy and clean images effectively, enabling the model to learn mappings even without paired data.
title Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.06107