ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.02395
55
0

The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception

3 June 2025
Xiaofeng Cong
Yu-Xin Zhang
Haoran Wei
Yeying Jin
Junming Hou
Jie Gui
Jing Zhang
Dacheng Tao
    DiffM
ArXiv (abs)PDFHTML
Main:8 Pages
13 Figures
Bibliography:3 Pages
3 Tables
Abstract

While nighttime image dehazing has been extensively studied, converting nighttime hazy images to daytime-equivalent brightness remains largely unaddressed. Existing methods face two critical limitations: (1) datasets overlook the brightness relationship between day and night, resulting in the brightness mapping being inconsistent with the real world during image synthesis; and (2) models do not explicitly incorporate daytime brightness knowledge, limiting their ability to reconstruct realistic lighting. To address these challenges, we introduce the Diffusion-Based Nighttime Dehazing (DiffND) framework, which excels in both data synthesis and lighting reconstruction. Our approach starts with a data synthesis pipeline that simulates severe distortions while enforcing brightness consistency between synthetic and real-world scenes, providing a strong foundation for learning night-to-day brightness mapping. Next, we propose a restoration model that integrates a pre-trained diffusion model guided by a brightness perception network. This design harnesses the diffusion model's generative ability while adapting it to nighttime dehazing through brightness-aware optimization. Experiments validate our dataset's utility and the model's superior performance in joint haze removal and brightness mapping.

View on arXiv
@article{cong2025_2506.02395,
  title={ The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception },
  author={ Xiaofeng Cong and Yu-Xin Zhang and Haoran Wei and Yeying Jin and Junming Hou and Jie Gui and Jing Zhang and Dacheng Tao },
  journal={arXiv preprint arXiv:2506.02395},
  year={ 2025 }
}
Comments on this paper