# Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing

arXiv: https://arxiv.org/abs/1805.05308 · HTML: https://mlsanity.com/paper/1805.05308/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2018.

## Built on by (most cited first, 30 of 79)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023)
- [MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing](https://mlsanity.com/paper/2207.05621/) (2022)
- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning](https://mlsanity.com/paper/2203.07677/) (2022)
- [Multi-Agent Image Restoration](https://mlsanity.com/paper/2503.09403/) (2025)
- [An Annotation-free Restoration Network for Cataractous Fundus Images](https://mlsanity.com/paper/2203.07737/) (2022)
- [A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning](https://mlsanity.com/paper/2106.03323/) (2021)
- [Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks](https://mlsanity.com/paper/2103.05422/) (2021)
- [Towards Domain Invariant Single Image Dehazing](https://mlsanity.com/paper/2101.10449/) (2021)
- [Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning](https://mlsanity.com/paper/2212.11473/) (2022)
- [Frequency Compensated Diffusion Model for Real-scene Dehazing](https://mlsanity.com/paper/2308.10510/) (2023)
- [Hybrid Agents for Image Restoration](https://mlsanity.com/paper/2503.10120/) (2025)
- [ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing](https://mlsanity.com/paper/2404.17825/) (2024)
- [Snow Mask Guided Adaptive Residual Network for Image Snow Removal](https://mlsanity.com/paper/2207.04754/) (2022)
- [Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training](https://mlsanity.com/paper/2503.15017/) (2025)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [Self-Supervised Video Desmoking for Laparoscopic Surgery](https://mlsanity.com/paper/2403.11192/) (2024)
- [A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth](https://mlsanity.com/paper/2206.06427/) (2022)
- [Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture](https://mlsanity.com/paper/2207.05605/) (2022)
- [Non-aligned supervision for Real Image Dehazing](https://mlsanity.com/paper/2303.04940/) (2023)
- [T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing](https://mlsanity.com/paper/2106.02809/) (2021)
- [When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Training](https://mlsanity.com/paper/2507.09524/) (2025)
- [Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration](https://mlsanity.com/paper/2210.01069/) (2022)
- [Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding](https://mlsanity.com/paper/2306.05675/) (2023)
- [RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image Dehazing](https://mlsanity.com/paper/2405.09083/) (2024)
- [Single Image Dehazing with An Independent Detail-Recovery Network](https://mlsanity.com/paper/2109.10492/) (2021)
- [Cross-Domain Car Detection Model with Integrated Convolutional Block Attention Mechanism](https://mlsanity.com/paper/2305.20055/) (2023)
- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media](https://mlsanity.com/paper/2102.05847/) (2021)

## Abstract (arXiv)

In this paper, we present an end-to-end network, called Cycle-Dehaze, for single image dehazing problem, which does not require pairs of hazy and corresponding ground truth images for training. That is, we train the network by feeding clean and hazy images in an unpaired manner. Moreover, the proposed approach does not rely on estimation of the atmospheric scattering model parameters. Our method enhances CycleGAN formulation by combining cycle-consistency and perceptual losses in order to improve the quality of textural information recovery and generate visually better haze-free images. Typically, deep learning models for dehazing take low resolution images as input and produce low resolution outputs. However, in the NTIRE 2018 challenge on single image dehazing, high resolution images were provided. Therefore, we apply bicubic downscaling. After obtaining low-resolution outputs from the network, we utilize the Laplacian pyramid to upscale the output images to the original resolution. We conduct experiments on NYU-Depth, I-HAZE, and O-HAZE datasets. Extensive experiments demonstrate that the proposed approach improves CycleGAN method both quantitatively and qualitatively.