Perceptual quality optimization of image super-resolution

Zhou, Wei, Li, Yixiao, Amirpour, Hadi, Hao, Xiaoshuai, Liu, Jiang, Wang, Peng and Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 2026. Perceptual quality optimization of image super-resolution. Presented at: 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 3-6 May 2026. ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE International Conference on Acoustics Speech and Signal Processing. IEEE; 1999, pp. 10537-10541. 10.1109/icassp55912.2026.11461596

Full text not available from this repository.

Abstract

Single image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual quality. To address this issue, we propose an Efficient Perceptual Bi-directional Attention Network (Efficient-PBAN) that explicitly optimizes SR towards human-preferred quality. Unlike patch-based quality models, Efficient-PBAN avoids extensive patch sampling and enables efficient image-level perception. The proposed framework is trained on our self-constructed SR quality dataset that covers a wide range of state-of-the-art SR methods with corresponding human opinion scores. Using this dataset, Efficient-PBAN learns to predict perceptual quality in a way that correlates strongly with subjective judgments. The learned metric is further integrated into SR training as a differentiable perceptual loss, enabling closed-loop alignment between reconstruction and perceptual assessment. Extensive experiments demonstrate that our approach delivers superior perceptual quality. Code is publicly available at https://github.com/Lighting-YXLI/Efficient-PBAN.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE; 1999
ISBN:	979-8-3315-6702-6
ISSN:	1520-6149
Last Modified:	04 Aug 2026 22:03
URI:	https://orca.cardiff.ac.uk/id/eprint/186874

Actions (repository staff only)

Edit Item