Domain Prompt Learning Framework for Real Image Dehazing
Kaihao Lin, Guoqing Wang, Yuhui Wu, Shuhang Gu, Xing Xu, Yang Yang · 2024
Supervised dehazing models trained on synthetic datasets exhibit severe performance degradation in real-world scenarios due to the domain gap. Unsupervised methods are proposed to process real hazy images, while they suffer from the complex training procedure. In this paper, we present a universal domain prompt learning framework (DPLF) for boosting the performance of supervised dehazing models in real scenarios by introducing prompt learning and well-designed domain adapters. We train the learnable text prompts by CLIP feature alignment, which can discriminate between real hazy and clean images, and use these prompts as unsupervised text constraints. Notably, the distribution gap between synthetic and real haze can be regarded as the difference of the haze-relevant style domain. Motivated by this, we design the style domain prompt adapter to align features from synthetic and real haze domains. Extensive experiments on real-world datasets demonstrate significant performance improvement of the baseline dehazing models with our DPLF.