Towards Unified Video Quality Assessment
Chen Feng, Tianhao Peng, Fan Zhang, David Bull

TL;DR
Unified-VQA introduces a versatile, interpretable video quality assessment framework that employs multiple experts and a diagnostic approach, outperforming existing methods across diverse video formats and artifacts.
Contribution
The paper presents a novel unified VQA model with a multi-expert architecture and diagnostic capabilities, enabling broad applicability and interpretability without retraining.
Findings
Outperforms 18 benchmark methods in VQA tasks
Provides interpretable artifact detection
Works across diverse video formats and resolutions
Abstract
Recent works in video quality assessment (VQA) typically employ monolithic models that typically predict a single quality score for each test video. These approaches cannot provide diagnostic, interpretable feedback, offering little insight into why the video quality is degraded. Most of them are also specialized, format-specific metrics rather than truly ``generic" solutions, as they are designed to learn a compromised representation from disparate perceptual domains. To address these limitations, this paper proposes Unified-VQA, a framework that provides a single, unified quality model applicable to various distortion types within multiple video formats by recasting generic VQA as a Diagnostic Mixture-of-Experts (MoE) problem. Unified-VQA employs multiple ``perceptual experts'' dedicated to distinct perceptual domains. A novel multi-proxy expert training strategy is designed to…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Video Quality Assessment · Visual Attention and Saliency Detection · Image Enhancement Techniques
