CLIP-DQA V2: Exploring CLIP for dehazed image quality assessment from a fragment-level perspective

Zeng, Yirui, Fu, Jun, Yue, Guanghui, Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 and Zhou, Wei 2025. CLIP-DQA V2: Exploring CLIP for dehazed image quality assessment from a fragment-level perspective. IEEE Signal Processing Letters 32 , pp. 3829-3833. 10.1109/lsp.2025.3615082

Full text not available from this repository.

Abstract

Contrastive Language-Image Pretraining (CLIP) models have demonstrated strong performance in blind dehazed image quality assessment (DQA), yet their efficiency remains a concern. In this letter, we introduce CLIP-DQA V2, which explores CLIP for efficient blind DQA from a fragment-level perspective. To effectively map fragments sampled from dehazed images to quality scores, CLIP-DQA V2 integrates two key components: (1) multi-modal prompt learning, which jointly optimizes CLIP’s image and text encoders for better alignment between fragments and quality-related text descriptions, and (2) a semantic consistency loss that alleviates the semantic degradation caused by fragment sampling. Experiments on two widely used benchmark datasets show that CLIP-DQA V2 reduces computational cost by nearly 45% compared to previous methods, while delivering more accurate quality predictions.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Additional Information:	License information from Publisher: LICENSE 1: URL: https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html, Start Date: 2025-01-01
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1070-9908
Last Modified:	14 Oct 2025 09:39
URI:	https://orca.cardiff.ac.uk/id/eprint/181645

Actions (repository staff only)

Edit Item