Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priors
This addresses the challenge of complex degradation in nighttime hazy images for computer vision applications, representing a novel method for a known bottleneck.
The paper tackles the problem of enhancing visibility in nighttime hazy images by proposing a framework that mutually and progressively reinforces haze and low-light priors, achieving superior performance on benchmarks with demonstrated generalizability to daytime dehazing and low-light enhancement.
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.