# Model-Based Single Image Deep Dehazing

arXiv: https://arxiv.org/abs/2111.10943 · HTML: https://mlsanity.com/paper/2111.10943/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 22 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [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)
- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing](https://mlsanity.com/paper/2001.06968/) (2020)
- [Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids](https://mlsanity.com/paper/2111.05700/) (2021)

## Built on by (most cited first, 3 of 3)

- [RB-Dust -- A Reference-based Dataset for Vision-based Dust Removal](https://mlsanity.com/paper/2306.07244/) (2023)
- [A Practical Framework for Unsupervised Structure Preservation Medical Image Enhancement](https://mlsanity.com/paper/2304.01864/) (2023)
- [Degraded Infrared Small Object Detection via Degradation-Adapted Physics-Guided Restoration](https://mlsanity.com/paper/2608.09311/) (2026)

## Abstract (arXiv)

Model-based single image dehazing algorithms restore images with sharp edges and rich details at the expense of low PSNR values. Data-driven ones restore images with high PSNR values but with low contrast, and even some remaining haze. In this paper, a novel single image dehazing algorithm is introduced by fusing model-based and data-driven approaches. Both transmission map and atmospheric light are initialized by the model-based methods, and refined by deep learning approaches which form a neural augmentation. Haze-free images are restored by using the transmission map and atmospheric light. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images.