文献类型：期刊文献

英文题名：DTIQA: a dual-path transformer framework for robust No-Reference Image Quality Assessment

作者：Ying, Fangli[1];AL-Garadi, Ahmed M.[1];Khalid, Mahzaib[1];Sun, Lihua[1];Phaphuangwittayakul, Aniwat[2];Zhou, Liting[3];Gurrin, Cathal[3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Technol, Shanghai 200237, Peoples R China;[2]Chiang Mai Univ, Int Coll Digital Innovat, Chiang Mai, Thailand;[3]Dublin City Univ, Sch Comp, Dublin, Ireland

年份：2026

卷号：42

期号：8

外文期刊名：VISUAL COMPUTER

收录：;EI(收录号：20262120768873);WOS:【SCI-EXPANDED(收录号:WOS:001771673900002)】；

基金：This work was supported in part by the Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (Grant No. JYB2025XDXM402), the National Major Scientific Instruments and Equipments Development Project of the National Natural Science Foundation of China (Grant No. 32327801), and the National Natural Science Foundation of China (Grant No. 12304553).

语种：英文

外文关键词：No-Reference Image Quality Assessment; Bidirectional cross-scale attention; Global-Local Gated Decomposition; Dual-path transformer; Perceptual quality

摘要：No-Reference Image Quality Assessment (NR-IQA) remains a challenging task due to the need to model the complex interplay between global semantic content and local distortion artifacts, central to human visual perception. Existing methods often rely on hand-crafted features, explicit feature separation, or multi-stage restoration pipelines, which fail to adaptively integrate cross-scale information. To address these limitations, we propose DTIQA, an end-to-end framework named Dual-Path Transformer for Image Quality Assessment. DTIQA introduces a Global-Local Gated Decomposition (GLGD) module to generate complementary content-aware and distortion-aware feature representations without explicit feature separation. A bidirectional cross-scale attention mechanism further refines these features, enabling adaptive convergence of contextual importance and degradation evidence. Extensive experiments on eight benchmark IQA datasets demonstrate that DTIQA achieves state-of-the-art performance, outperforming competing methods with strong generalization and stable training dynamics. The official implementation is available at https://github.com/algaradi/DTIQA (DOI: https://doi.org/10.5281/zenodo.18842363).