No-reference image quality assessment via perception-guided distortion representation refinement

Zhang, Yutong, Zhou, Siqi, Liang, Feng, Wang, Huasheng, Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 and Lou, Jianxun 2026. No-reference image quality assessment via perception-guided distortion representation refinement. IEEE Signal Processing Letters 10.1109/lsp.2026.3725501

Full text not available from this repository.

Abstract

No-Reference Image Quality Assessment (NR-IQA) aims to predict perceptual image quality from distorted images without reference signals. Existing NR-IQA methods often incorporate visual attention through external weighting or feature fusion, while semantic and distortion cues are often not sufficiently organized for quality prediction, limiting perceptually guided distortion refinement. To address these limitations, this paper proposes a perception-guided distortion representation refinement framework for NR-IQA. Specifically, the Perceptual Adaptive Network (PAN) converts visual attention priors into spatially varying affine parameters for feature normalization, enabling perceptual-prior-conditioned modulation of intermediate distortion responses. The Semantic-distortion Asymmetric Cross-Gated Head (SD-ACG) further organizes the quality representation into semantic-aware and distortion-sensitive branches, using semantic-guided residual cross-gating and orthogonal branch regularization to refine distortion representations while reducing branch redundancy. Experiments on standard synthetic and authentic IQA benchmarks demonstrate consistent performance improvements across diverse distortion settings.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Computational & Mathematical Sciences Schools > Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1070-9908
Last Modified:	24 Aug 2026 11:32
URI:	https://orca.cardiff.ac.uk/id/eprint/189147

Actions (repository staff only)

Edit Item