# End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks

arXiv: https://arxiv.org/abs/1902.01374 · HTML: https://mlsanity.com/paper/1902.01374/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2019.

## Built on by (most cited first, 15 of 15)

- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [NightHaze: Nighttime Image Dehazing via Self-Prior Learning](https://mlsanity.com/paper/2403.07408/) (2024)
- [A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning](https://mlsanity.com/paper/2106.03323/) (2021)
- [Frequency Compensated Diffusion Model for Real-scene Dehazing](https://mlsanity.com/paper/2308.10510/) (2023)
- [Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing](https://mlsanity.com/paper/2503.13147/) (2025)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth](https://mlsanity.com/paper/2206.06427/) (2022)
- [Progressive Frequency-Aware Network for Laparoscopic Image Desmoking](https://mlsanity.com/paper/2312.12023/) (2023)
- [Seeing Beyond Haze: Generative Nighttime Image Dehazing](https://mlsanity.com/paper/2503.08073/) (2025)
- [UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior](https://mlsanity.com/paper/2501.06818/) (2025)
- [Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing](https://mlsanity.com/paper/2207.11250/) (2022)
- [ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing](https://mlsanity.com/paper/2503.17488/) (2025)
- [A GAN-Based Input-Size Flexibility Model for Single Image Dehazing](https://mlsanity.com/paper/2102.09796/) (2021)
- [Unpaired Quad-Path Cycle Consistent Adversarial Networks for Single Image Defogging](https://mlsanity.com/paper/2202.09553/) (2022)
- [From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing](https://mlsanity.com/paper/2511.11944/) (2025)

## Abstract (arXiv)

Single image defogging is a classical and challenging problem in computer vision. Existing methods towards this problem mainly include handcrafted priors based methods that rely on the use of the atmospheric degradation model and learning based approaches that require paired fog-fogfree training example images. In practice, however, prior-based methods are prone to failure due to their own limitations and paired training data are extremely difficult to acquire. Inspired by the principle of CycleGAN network, we have developed an end-to-end learning system that uses unpaired fog and fogfree training images, adversarial discriminators and cycle consistency losses to automatically construct a fog removal system. Similar to CycleGAN, our system has two transformation paths; one maps fog images to a fogfree image domain and the other maps fogfree images to a fog image domain. Instead of one stage mapping, our system uses a two stage mapping strategy in each transformation path to enhance the effectiveness of fog removal. Furthermore, we make explicit use of prior knowledge in the networks by embedding the atmospheric degradation principle and a sky prior for mapping fogfree images to the fog images domain. In addition, we also contribute the first real world nature fog-fogfree image dataset for defogging research. Our multiple real fog images dataset (MRFID) contains images of 200 natural outdoor scenes. For each scene, there are one clear image and corresponding four foggy images of different fog densities manually selected from a sequence of images taken by a fixed camera over the course of one year. Qualitative and quantitative comparison against several state-of-the-art methods on both synthetic and real world images demonstrate that our approach is effective and performs favorably for recovering a clear image from a foggy image.