HazeCLIP: Towards Language Guided Real-World Image Dehazing

TL;DR

HazeCLIP introduces a language-guided framework that leverages CLIP to adapt pre-trained dehazing models for improved performance on real-world hazy images, addressing domain shift issues.

Contribution

The paper presents a novel language-guided adaptation method using CLIP to enhance real-world image dehazing performance of existing models.

Findings

Achieves state-of-the-art results on real-world dehazing datasets.

Effectively identifies hazy regions using language prompts.

Improves visual and quantitative dehazing metrics.

Abstract

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.