HazeCLIP: Towards Language Guided Real-World Image Dehazing
This work addresses domain shift issues in image dehazing for practical applications, representing an incremental improvement by adapting existing methods with language guidance.
The paper tackles the problem of real-world image dehazing by introducing HazeCLIP, a language-guided adaptation framework that enhances pre-trained networks, achieving state-of-the-art performance as demonstrated through visual quality and image quality assessment metrics.
Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets. However, they often struggle with real-world hazy images due to domain shift, limiting their practical applicability. This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks. Inspired by the Contrastive Language-Image Pre-training (CLIP) model's ability to distinguish between hazy and clean images, we leverage it to evaluate dehazing results. Combined with a region-specific dehazing technique and tailored prompt sets, the CLIP model accurately identifies hazy areas, providing a high-quality, human-like prior that guides the fine-tuning process of pre-trained networks. Extensive experiments demonstrate that HazeCLIP achieves state-of-the-art performance in real-word image dehazing, evaluated through both visual quality and image quality assessment metrics. Codes are available at https://github.com/Troivyn/HazeCLIP.