Temporal inconsistency guidance for super-resolution video quality assessment

Li, Yixiao, Yang, Xiaoyuan, Liu, Weide, Jin, Xin, Jia, Xu, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884, Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 and Zhou, Wei 2026. Temporal inconsistency guidance for super-resolution video quality assessment. Presented at: The 40th Annual AAAI Conference on Artificial Intelligence, Singapore, 20-27 January 2026. Proceedings of the AAAI Conference on Artificial Intelligence. , vol.40 (8) pp. 6681-6689. 10.1609/aaai.v40i8.37599

PDF - Accepted Post-Print Version Download (9MB)

Abstract

As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an increasing demand for specialized video quality assessment (VQA) methods tailored to SR-generated content. One critical factor affecting perceived quality is temporal inconsistency, which refers to irregularities between consecutive frames. However, existing VQA approaches rarely quantify this phenomenon or explicitly investigate its relationship with human perception. Moreover, SR videos exhibit amplified inconsistency levels as a result of enhancement processes. In this paper, we propose Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (TIG-SVQA) that underscores the critical role of temporal inconsistency in guiding the quality assessment of SR videos. We first design a perception-oriented approach to quantify frame-wise temporal inconsistency. Based on this, we introduce the Inconsistency Highlighted Spatial Module, which localizes inconsistent regions at both coarse and fine scales. Inspired by the human visual system, we further develop an Inconsistency Guided Temporal Module that performs progressive temporal feature aggregation: (1) a consistency-aware fusion stage in which a visual memory capacity block adaptively determines the information load of each temporal segment based on inconsistency levels, and (2) an informative filtering stage for emphasizing quality-related features. Extensive experiments on both single-frame and multi-frame SR video scenarios demonstrate that our method significantly outperforms state-of-the-art VQA approaches.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Date of First Compliant Deposit:	5 February 2026
Date of Acceptance:	20 January 2026
Last Modified:	24 Mar 2026 11:45
URI:	https://orca.cardiff.ac.uk/id/eprint/184440

Actions (repository staff only)

Edit Item