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

TL;DR

This paper introduces DiffND, a diffusion-based framework for nighttime dehazing that improves brightness consistency and realistic lighting reconstruction by combining data synthesis with a brightness-guided diffusion model.

Contribution

The paper presents a novel diffusion-based nighttime dehazing method that explicitly incorporates brightness perception and improves realism in lighting and haze removal.

Findings

Outperforms existing methods in haze removal and brightness mapping

Provides a new dataset for nighttime dehazing with brightness consistency

Demonstrates superior visual quality and realism in reconstructed images

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.