# Dual-Scale Single Image Dehazing Via Neural Augmentation

arXiv: https://arxiv.org/abs/2209.05913 · HTML: https://mlsanity.com/paper/2209.05913/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 62 references that are in the map.
- First posted on arXiv 13 Sep 2022.

## Builds on (most cited first, 19 of 19)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent](https://mlsanity.com/paper/1902.06720/) (2019)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [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)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020)
- [FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing](https://mlsanity.com/paper/2001.06968/) (2020)
- [Material Recognition in the Wild with the Materials in Context Database](https://mlsanity.com/paper/1412.0623/) (2014)
- [Gradient descent GAN optimization is locally stable](https://mlsanity.com/paper/1706.04156/) (2017)
- [Unsupervised Single Image Dehazing Using Dark Channel Prior Loss](https://mlsanity.com/paper/1812.07051/) (2018)
- [Approximation and Convergence Properties of Generative Adversarial Learning](https://mlsanity.com/paper/1705.08991/) (2017)
- [Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids](https://mlsanity.com/paper/2111.05700/) (2021)
- [Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning](https://mlsanity.com/paper/2007.02042/) (2020)

## Built on by (most cited first, 10 of 10)

- [Vision-Based Traffic Accident Detection and Anticipation: A Survey](https://mlsanity.com/paper/2308.15985/) (2023)
- [Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning](https://mlsanity.com/paper/2212.11473/) (2022)
- [HazeCLIP: Towards Language Guided Real-World Image Dehazing](https://mlsanity.com/paper/2407.13719/) (2024)
- [VIFNet: An End-to-end Visible-Infrared Fusion Network for Image Dehazing](https://mlsanity.com/paper/2404.07790/) (2024)
- [Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing](https://mlsanity.com/paper/2210.16057/) (2022)
- [WaveletFormerNet: A Transformer-based Wavelet Network for Real-world Non-homogeneous and Dense Fog Removal](https://mlsanity.com/paper/2401.04550/) (2024)
- [UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior](https://mlsanity.com/paper/2501.06818/) (2025)
- [Single Image Deraining via Feature-based Deep Convolutional Neural Network](https://mlsanity.com/paper/2305.02100/) (2023)
- [DedustNet: A Frequency-dominated Swin Transformer-based Wavelet Network for Agricultural Dust Removal](https://mlsanity.com/paper/2401.04750/) (2024)
- [Multi-Branch Non-Homogeneous Image Dehazing via Concentration Partitioning and Image Fusion](https://mlsanity.com/paper/2605.00885/) (2026)

## Abstract (arXiv)

Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free images with high PSNR and SSIM values for synthetic hazy images but with low contrast, and even some remaining haze for real world hazy images. In this paper, a novel single image dehazing algorithm is introduced by combining model-based and data-driven approaches. Both transmission map and atmospheric light are first estimated by the model-based methods, and then refined by dual-scale generative adversarial networks (GANs) based approaches. The resultant algorithm forms a neural augmentation which converges very fast while the corresponding data-driven approach might not converge. Haze-free images are restored by using the estimated transmission map and atmospheric light as well as the Koschmiederlaw. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images.