Scholarlink

<p>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 <a href="https://github.com/algaradi/DTIQA">https://github.com/algaradi/DTIQA</a> (DOI: <a href="https://doi.org/10.5281/zenodo.18842363">https://doi.org/10.5281/zenodo.18842363</a>).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 发表日期：

    2026年5月20日

查看全文
  • Fangli Ying,
  • Ahmed M. AL-Garadi,
  • Mahzaib Khalid,
  • Lihua Sun,
  • Aniwat Phaphuangwittayakul,
  • Liting Zhou,
  • Cathal Gurrin

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).