# CodecArena: Codec Quality Assessment via Visual Reinforcement Learning

arXiv: https://arxiv.org/abs/2608.09139 · HTML: https://mlsanity.com/paper/2608.09139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/1905.00737/) (2019)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [A Technical Overview of AV1](https://mlsanity.com/paper/2008.06091/) (2020)
- [Neural Video Compression using GANs for Detail Synthesis and Propagation](https://mlsanity.com/paper/2107.12038/) (2021)
- [VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning](https://mlsanity.com/paper/2506.18564/) (2025)
- [Generative Neural Video Compression via Video Diffusion Prior](https://mlsanity.com/paper/2512.05016/) (2025)
- [Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance](https://mlsanity.com/paper/2512.07480/) (2025)
- [BVI-AOM: A New Training Dataset for Deep Video Compression Optimization](https://mlsanity.com/paper/2408.03265/) (2024)
- [Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission](https://mlsanity.com/paper/2512.24300/) (2025)
- [PICD: Versatile Perceptual Image Compression with Diffusion Rendering](https://mlsanity.com/paper/2505.05853/) (2025)
- [CoD: A Diffusion Foundation Model for Image Compression](https://mlsanity.com/paper/2511.18706/) (2025)
- [Generative Video Compression with One-Dimensional Latent Representation](https://mlsanity.com/paper/2603.15302/) (2026)

## Abstract (arXiv)

Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly optimized neural networks and generative codecs that exploit the priors of video generation models. Yet the dominant metrics, LPIPS and DISTS, measure feature and texture similarity rather than content fidelity: a reconstruction that hallucinates a wrong face or blurs text into convincing strokes can still score well, even when a human rejects it instantly. To address this, we propose CodecArena, the first vision-language framework for video coding quality assessment, casting codec evaluation as source-conditioned comparative reasoning between a reference and its reconstructions. We optimize CodecArena with Facet-GRPO, a visual reinforcement learning scheme that aligns pairwise codec preferences while grounding the verdict in five fidelity facets: identity, objects, text, texture, and temporal consistency. Its facet-anchored reward uses automatically derived facet directions as weak anchors, rather than human per-facet labels, to prevent any single sub-score from dominating the holistic preference and to yield interpretable fine-grained quality judgments. To support training and evaluation in this underexplored regime, we construct two complementary resources: CodecArena-1K, a fully automatic preference dataset of 1,500 comparison groups built from traditional, neural, and generative codec reconstructions with fused vision-language and objective supervision; and CodecArena-Bench, a human-ranked benchmark with source-disjoint videos for fair out-of-domain evaluation. Extensive experiments demonstrate that CodecArena achieves state-of-the-art agreement with human judgments on source-disjoint content across diverse codecs and bitrates, surpassing perceptual metrics and prior vision-language evaluators.