Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priors

TL;DR

This paper introduces a novel framework for enhancing nighttime hazy images by mutually reinforcing haze and low-light priors, utilizing multi-level experts and a frequency-aware router for progressive and robust image restoration.

Contribution

The proposed method uniquely integrates haze and low-light priors with multi-level experts and a frequency-aware router for improved nighttime haze removal.

Findings

Outperforms existing methods on nighttime dehazing benchmarks

Demonstrates effectiveness in daytime dehazing and low-light enhancement

Achieves superior qualitative and quantitative results

Abstract

Enhancing the visibility of nighttime hazy images is challenging due to the complex degradation distributions. Existing methods mainly address a single type of degradation (e.g., haze or low-light) at a time, ignoring the interplay of different degradation types and resulting in limited visibility improvement. We observe that the domain knowledge shared between low-light and haze priors can be reinforced mutually for better visibility. Based on this key insight, in this paper, we propose a novel framework that enhances visibility in nighttime hazy images by reinforcing the intrinsic consistency between haze and low-light priors mutually and progressively. In particular, our model utilizes image-, patch-, and pixel-level experts that operate across visual and frequency domains to recover global scene structure, regional patterns, and fine-grained details progressively. A frequency-aware router is further introduced to adaptively guide the contribution of each expert, ensuring robust image restoration. Extensive experiments demonstrate the superior performance of our model on nighttime dehazing benchmarks both quantitatively and qualitatively. Moreover, we showcase the generalizability of our model in daytime dehazing and low-light enhancement tasks.