English

Progressive Feature Fusion Network for Realistic Image Dehazing

Computer Vision and Pattern Recognition 2018-10-05 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1810.02283,
  title  = {Progressive Feature Fusion Network for Realistic Image Dehazing},
  author = {Kangfu Mei and Aiwen Jiang and Juncheng Li and Mingwen Wang},
  journal= {arXiv preprint arXiv:1810.02283},
  year   = {2018}
}

Comments

14 pages, 7 figures, 1 tables, accepted by ACCV2018

R2 v1 2026-06-23T04:28:39.050Z