The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception
This work addresses nighttime dehazing for computer vision applications, but it is incremental as it builds on existing diffusion models with brightness-aware optimizations.
The paper tackles the problem of nighttime image dehazing by converting hazy images to daytime-equivalent brightness, addressing limitations in existing datasets and models, and introduces the DiffND framework that achieves superior performance in joint haze removal and brightness mapping.
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.