# Towards Unified Video Quality Assessment

arXiv: https://arxiv.org/abs/2512.02224 · HTML: https://mlsanity.com/paper/2512.02224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 35 of its 72 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 35)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content](https://mlsanity.com/paper/2005.14354/) (2020)
- [Auxiliary Tasks in Multi-task Learning](https://mlsanity.com/paper/1805.06334/) (2018)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception](https://mlsanity.com/paper/2108.08505/) (2021)
- [Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training](https://mlsanity.com/paper/2011.04263/) (2020)
- [BVI-DVC: A Training Database for Deep Video Compression](https://mlsanity.com/paper/2003.13552/) (2020)
- [HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content](https://mlsanity.com/paper/2304.13625/) (2023)
- [ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction](https://mlsanity.com/paper/2010.13715/) (2020)
- [C3DVQA: Full-Reference Video Quality Assessment with 3D Convolutional Neural Network](https://mlsanity.com/paper/1910.13646/) (2019)
- [ChipQA: No-Reference Video Quality Prediction via Space-Time Chips](https://mlsanity.com/paper/2109.08726/) (2021)
- [BBAND Index: A No-Reference Banding Artifact Predictor](https://mlsanity.com/paper/2002.11891/) (2020)
- [Enhancing Blind Video Quality Assessment with Rich Quality-aware Features](https://mlsanity.com/paper/2405.08745/) (2024)
- [PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild](https://mlsanity.com/paper/2405.17765/) (2024)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [Learning to Blindly Assess Image Quality in the Laboratory and Wild](https://mlsanity.com/paper/1907.00516/) (2019)
- [Subjective Assessment of High Dynamic Range Videos Under Different Ambient Conditions](https://mlsanity.com/paper/2209.10005/) (2022)
- [CAMBI: Contrast-aware Multiscale Banding Index](https://mlsanity.com/paper/2102.00079/) (2021)

## Abstract (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.