# Deep Variational Bayesian Modeling of Haze Degradation Process

arXiv: https://arxiv.org/abs/2412.03745 · HTML: https://mlsanity.com/paper/2412.03745/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 18 of 18)

- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [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)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [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)
- [Variational Denoising Network: Toward Blind Noise Modeling and Removal](https://mlsanity.com/paper/1908.11314/) (2019)
- [NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images](https://mlsanity.com/paper/2005.03560/) (2020)
- [FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing](https://mlsanity.com/paper/2001.06968/) (2020)
- [Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration](https://mlsanity.com/paper/1903.08817/) (2019)
- [From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data](https://mlsanity.com/paper/2108.02934/) (2021)
- [An Alternative Probabilistic Interpretation of the Huber Loss](https://mlsanity.com/paper/1911.02088/) (2019)
- [Joint Transmission Map Estimation and Dehazing using Deep Networks](https://mlsanity.com/paper/1708.00581/) (2017)
- [Progressive Feature Fusion Network for Realistic Image Dehazing](https://mlsanity.com/paper/1810.02283/) (2018)
- [A Deep Variational Bayesian Framework for Blind Image Deblurring](https://mlsanity.com/paper/2106.02884/) (2021)

## Built on by (most cited first, 5 of 5)

- [HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing](https://mlsanity.com/paper/2509.18190/) (2025)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models](https://mlsanity.com/paper/2510.13315/) (2025)
- [Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding](https://mlsanity.com/paper/2604.13313/) (2026)
- [PRISM: Latent Composition Consistency for Single-Image Reflection Removal](https://mlsanity.com/paper/2606.31513/) (2026)

## Abstract (arXiv)

Relying on the representation power of neural networks, most recent works have often neglected several factors involved in haze degradation, such as transmission (the amount of light reaching an observer from a scene over distance) and atmospheric light. These factors are generally unknown, making dehazing problems ill-posed and creating inherent uncertainties. To account for such uncertainties and factors involved in haze degradation, we introduce a variational Bayesian framework for single image dehazing. We propose to take not only a clean image and but also transmission map as latent variables, the posterior distributions of which are parameterized by corresponding neural networks: dehazing and transmission networks, respectively. Based on a physical model for haze degradation, our variational Bayesian framework leads to a new objective function that encourages the cooperation between them, facilitating the joint training of and thereby boosting the performance of each other. In our framework, a dehazing network can estimate a clean image independently of a transmission map estimation during inference, introducing no overhead. Furthermore, our model-agnostic framework can be seamlessly incorporated with other existing dehazing networks, greatly enhancing the performance consistently across datasets and models.