Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models
This work addresses the limitation of synthetic data-trained models for real-world adverse weather restoration, which is an incremental improvement for applications like autonomous driving and surveillance.
The paper tackles the problem of adverse weather image restoration in real-world scenarios by proposing a semi-supervised learning framework that uses vision-language models to enhance clearness and semantics, achieving superior results compared to state-of-the-art methods.
This paper addresses the limitations of adverse weather image restoration approaches trained on synthetic data when applied to real-world scenarios. We formulate a semi-supervised learning framework employing vision-language models to enhance restoration performance across diverse adverse weather conditions in real-world settings. Our approach involves assessing image clearness and providing semantics using vision-language models on real data, serving as supervision signals for training restoration models. For clearness enhancement, we use real-world data, utilizing a dual-step strategy with pseudo-labels assessed by vision-language models and weather prompt learning. For semantic enhancement, we integrate real-world data by adjusting weather conditions in vision-language model descriptions while preserving semantic meaning. Additionally, we introduce an effective training strategy to bootstrap restoration performance. Our approach achieves superior results in real-world adverse weather image restoration, demonstrated through qualitative and quantitative comparisons with state-of-the-art works.