Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment
Yixiao Li, Xiaoyuan Yang, Weide Liu, Xin Jin, Xu Jia, Yukun Lai, Paul L Rosin, Haotao Liu, and Wei Zhou

TL;DR
This paper introduces TIG-SVQA, a novel video quality assessment method that explicitly quantifies and leverages temporal inconsistency to better evaluate super-resolution videos, outperforming existing approaches.
Contribution
The paper proposes a perception-oriented temporal inconsistency quantification method and a novel guidance framework for SR video quality assessment, emphasizing the role of inconsistency in perceived quality.
Findings
Outperforms state-of-the-art VQA methods on SR videos
Effectively localizes inconsistent regions at multiple scales
Improves correlation with human perception in quality assessment
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 \textit{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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsImage and Video Quality Assessment · Advanced Image Processing Techniques · Image and Signal Denoising Methods
