# A GAN-Based Input-Size Flexibility Model for Single Image Dehazing

arXiv: https://arxiv.org/abs/2102.09796 · HTML: https://mlsanity.com/paper/2102.09796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 19 Feb 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Gated Fusion Network for Single Image Dehazing](https://mlsanity.com/paper/1804.00213/) (2018)
- [SNIPER: Efficient Multi-Scale Training](https://mlsanity.com/paper/1805.09300/) (2018)
- [Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing](https://mlsanity.com/paper/1805.05308/) (2018)
- [End-to-End United Video Dehazing and Detection](https://mlsanity.com/paper/1709.03919/) (2017)
- [End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks](https://mlsanity.com/paper/1902.01374/) (2019)
- [FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network](https://mlsanity.com/paper/1906.04334/) (2019)
- [Single Image Dehazing Using Ranking Convolutional Neural Network](https://mlsanity.com/paper/2001.05246/) (2020)
- [Improved Techniques for Learning to Dehaze and Beyond: A Collective Study](https://mlsanity.com/paper/1807.00202/) (2018)
- [The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing](https://mlsanity.com/paper/1805.03305/) (2018)

## Abstract (arXiv)

Image-to-image translation based on generative adversarial network (GAN) has achieved state-of-the-art performance in various image restoration applications. Single image dehazing is a typical example, which aims to obtain the haze-free image of a haze one. This paper concentrates on the challenging task of single image dehazing. Based on the atmospheric scattering model, a novel model is designed to directly generate the haze-free image. The main challenge of image dehazing is that the atmospheric scattering model has two parameters, i.e., transmission map and atmospheric light. When they are estimated respectively, the errors will be accumulated to compromise the dehazing quality. Considering this reason and various image sizes, a novel input-size flexibility conditional generative adversarial network (cGAN) is proposed for single image dehazing, which is input-size flexibility at both training and test stages for image-to-image translation with cGAN framework. A simple and effective U-connection residual network (UR-Net) is proposed to combine the generator and adopt the spatial pyramid pooling (SPP) to design the discriminator. Moreover, the model is trained with multi-loss function, in which the consistency loss is a novel designed loss in this paper. Finally, a multi-scale cGAN fusion model is built to realize state-of-the-art single image dehazing performance. The proposed models receive a haze image as input and directly output a haze-free one. Experimental results demonstrate the effectiveness and efficiency of the proposed models.