paper-with-me

홈 › Papers

Towards Unified Video Quality Assessment

2025-12-01 · Chen Feng, Tianhao Peng, Fan Zhang, David Bull arxiv

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 optimize each expert using a ranking-inspired loss, guided by the most suitable proxy metric for its domain. We also integrated a diagnostic multi-task head into this framework to generate a global quality score and an interpretable multi-dimensional artifact vector, which is optimized using a weakly-supervised learning strategy, leveraging the known properties of the large-scale training database generated for this work. With static model parameters (without retraining or fine-tuning), Unified-VQA demonstrates consistent and superior performance compared to over 18 benchmark methods for both generic VQA and diagnostic artifact detection tasks across 17 databases containing diverse streaming artifacts in HD, UHD, HDR and HFR formats. This work represents an important step towards practical, actionable, and interpretable video quality assessment.

📄 PDF Abstract BibTeX arXiv:2512.02224

Code (0)

등록된 구현이 없습니다.

Tasks

Video Quality AssessmentArtifact Detection

Similar Papers 제목 키워드 기반

Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model

2024-07-31 · Zhichao Zhang, Wei Sun, Xinyue Li, Jun Jia 외

In recent years, artificial intelligence (AI)-driven video generation has gained significant attention. Consequently, there is a growing need for accurate video quality assessment (VQA) metrics to evaluate the perceptual…

BenchmarkingLarge Language ModelVideo AlignmentVideo Generation+2

Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training

2020-11-09 · Dingquan Li, Tingting Jiang, Ming Jiang

Video quality assessment (VQA) is an important problem in computer vision. The videos in computer vision applications are usually captured in the wild. We focus on automatically assessing the quality of in-the-wild video…

Video Quality Assessment

One Transform To Compute Them All: Efficient Fusion-Based Full-Reference Video Quality Assessment

2023-04-06 · Abhinau K. Venkataramanan, Cosmin Stejerean, Ioannis Katsavounidis, Alan C. Bovik

The Visual Multimethod Assessment Fusion (VMAF) algorithm has recently emerged as a state-of-the-art approach to video quality prediction, that now pervades the streaming and social media industry. However, since VMAF re…

AllComputational EfficiencyVideo CompressionVideo Quality Assessment

UNQA: Unified No-Reference Quality Assessment for Audio, Image, Video, and Audio-Visual Content

2024-07-29 · Yuqin Cao, Xiongkuo Min, Yixuan Gao, Wei Sun 외

As multimedia data flourishes on the Internet, quality assessment (QA) of multimedia data becomes paramount for digital media applications. Since multimedia data includes multiple modalities including audio, image, video…

A strong baseline for image and video quality assessment

2021-11-13 · Shaoguo Wen, Junle Wang

In this work, we present a simple yet effective unified model for perceptual quality assessment of image and video. In contrast to existing models which usually consist of complex network architecture, or rely on the con…

Video Quality Assessment