Skip to content

TaoLi-TL/FOVM

Repository files navigation

Real-World Nighttime Image Dehazing via Bayesian-Based Fractional-Order Variational Model

This repository contains the implementation of our paper: "Real-World Nighttime Image Dehazing via Bayesian-Based Fractional-Order Variational Model".

Authors

Yun Liu1, Tao Li1, Zichen Zhou2, Wenqi Ren3, Weisi Lin4

  1. College of Artificial Intelligence, Southwest University, Chongqing, China
  2. China University of Petroleum, China
  3. School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China
  4. College of Computing and Data Science, Nanyang Technological University (NTU), Singapore

Methodology

Overall Flowchart

The following flowchart illustrates the proposed method for nighttime image dehazing:

Flowchart of our proposed method


Installation & Usage

Prerequisites

  • MATLAB (Tested on R2021a or later)

Run the Demo

  1. Place your hazy nighttime images in the input/ folder.
  2. Run the demo.m script:
    demo
  3. The processed images will be saved in the output/ folder.

Citation

If you find this work useful for your research, please cite our paper:

@article{Liu2026RealWorldNighttime,
  title={Real-World Nighttime Image Dehazing via Bayesian-Based Fractional-Order Variational Model},
  author={Liu, Yun and Li, Tao and Zhou, Zichen and Ren, Wenqi and Lin, Weisi},
  journal={},
  year={2026}
}

About

[IEEE TIP'26] Real-World Nighttime Image Dehazing via Bayesian-Based Fractional-Order Variational Model

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages