# Progressive Feature Fusion Network for Realistic Image Dehazing

arXiv: https://arxiv.org/abs/1810.02283 · HTML: https://mlsanity.com/paper/1810.02283/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2018.

## Built on by (most cited first, 13 of 13)

- [Towards Domain Invariant Single Image Dehazing](https://mlsanity.com/paper/2101.10449/) (2021)
- [Efficient and Accurate Multi-scale Topological Network for Single Image Dehazing](https://mlsanity.com/paper/2102.12135/) (2021)
- [Single UHD Image Dehazing via Interpretable Pyramid Network](https://mlsanity.com/paper/2202.08589/) (2022)
- [Snow Mask Guided Adaptive Residual Network for Image Snow Removal](https://mlsanity.com/paper/2207.04754/) (2022)
- [Single Image Dehazing with An Independent Detail-Recovery Network](https://mlsanity.com/paper/2109.10492/) (2021)
- [Deep Variational Bayesian Modeling of Haze Degradation Process](https://mlsanity.com/paper/2412.03745/) (2024)
- [ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media](https://mlsanity.com/paper/2102.05847/) (2021)
- [4K-HAZE: A Dehazing Benchmark with 4K Resolution Hazy and Haze-Free Images](https://mlsanity.com/paper/2303.15848/) (2023)
- [Deep Semantic Statistics Matching (D2SM) Denoising Network](https://mlsanity.com/paper/2207.09302/) (2022)
- [FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing](https://mlsanity.com/paper/2407.00972/) (2024)
- [How to deal with glare for improved perception of Autonomous Vehicles](https://mlsanity.com/paper/2404.10992/) (2024)
- [Multi-Exposure Image Fusion via Distilled 3D LUT Grid with Editable Mode](https://mlsanity.com/paper/2412.13749/) (2024)
- [CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture](https://mlsanity.com/paper/2505.01882/) (2025)

## Abstract (arXiv)

Single image dehazing is a challenging ill-posed restoration problem. Various prior-based and learning-based methods have been proposed. Most of them follow a classic atmospheric scattering model which is an elegant simplified physical model based on the assumption of single-scattering and homogeneous atmospheric medium. The formulation of haze in realistic environment is more complicated. In this paper, we propose to take its essential mechanism as "black box", and focus on learning an input-adaptive trainable end-to-end dehazing model. An U-Net like encoder-decoder deep network via progressive feature fusions has been proposed to directly learn highly nonlinear transformation function from observed hazy image to haze-free ground-truth. The proposed network is evaluated on two public image dehazing benchmarks. The experiments demonstrate that it can achieve superior performance when compared with popular state-of-the-art methods. With efficient GPU memory usage, it can satisfactorily recover ultra high definition hazed image up to 4K resolution, which is unaffordable by many deep learning based dehazing algorithms.