CodecArena: Codec Quality Assessment via Visual Reinforcement Learning

• URL: http://arxiv.org/abs/2608.09139v1
• Date: Mon, 10 Aug 2026 05:37:06 GMT
• Title: CodecArena: Codec Quality Assessment via Visual Reinforcement Learning
• Abstract summary: We propose CodecArena, the first vision-language framework for video coding quality assessment.<n>CodecArena casts evaluation as source-conditioned comparative reasoning between a reference and its reconstructions.<n>Its facet-anchored reward uses automatically derived facet directions as weak anchors, rather than human per-facet labels.
• Score: 70.59130074737446
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs [16.429817532129388]
  FDIM is a feature-distance-based generic video quality metric for both traditional and neural video codecs.<n>We trained FDIM on a large-scale subjective quality assessment dataset (DCV) consisting of over 16k video sequences.
  arXiv  Detail & Related papers  (2026-04-27T07:19:05Z)
• OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence [113.73007911004446]
  OneVision-Encoder encodes video by compressing visual structure into semantic meaning.<n>Codec-aligned, patch-level sparsity is a foundational principle, enabling OV-Encoder as a scalable engine for next-generation visual generalists.
  arXiv  Detail & Related papers  (2026-02-09T14:06:17Z)
• SCENE: Semantic-aware Codec Enhancement with Neural Embeddings [9.6489283335586]
  We propose a semantic-aware pre-processing framework that enhances perceptual fidelity.<n>Our method integrates semantic embeddings from a vision-language model into an efficient convolutional architecture.<n>Our results show that semantic-aware pre-processing is an effective approach for enhancing compressed video streams.
  arXiv  Detail & Related papers  (2026-01-29T05:41:28Z)
• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction [83.50898344094153]
  VQRAE produces Continuous semantic features for image understanding and tokens for visual generation within a unified tokenizer.<n>Design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens.<n>VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction.
  arXiv  Detail & Related papers  (2025-11-28T17:26:34Z)
• Baseline Systems For The 2025 Low-Resource Audio Codec Challenge [0.0]
  The Low-Resource Audio Codec (LRAC) Challenge aims to advance neural audio coding for deployment in resource-constrained environments.<n>This paper presents the official baseline systems for both tracks in the 2025 LRAC Challenge.
  arXiv  Detail & Related papers  (2025-09-30T20:36:58Z)
• SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec [83.61175662066364]
  Speech codecs serve as a crucial bridge in unifying speech and text language models.<n>Existing methods face several challenges in semantic encoding.<n>We propose SecoustiCodec, a cross-modal aligned low-bitrate streaming speech codecs.
  arXiv  Detail & Related papers  (2025-08-04T19:22:14Z)
• Prediction and Reference Quality Adaptation for Learned Video Compression [54.58691829087094]
  Temporal prediction is one of the most important technologies for video compression.<n>Traditional video codecs adaptively decide the optimal coding mode according to the prediction quality and reference quality.<n>We propose a confidence-based prediction quality adaptation (PQA) module and a reference quality adaptation (RQA) module.
  arXiv  Detail & Related papers  (2024-06-20T09:03:26Z)
• Compression-Realized Deep Structural Network for Video Quality Enhancement [78.13020206633524]
  This paper focuses on the task of quality enhancement for compressed videos. Most of the existing methods lack a structured design to optimally leverage the priors within compression codecs. A new paradigm is urgently needed for a more conscious'' process of quality enhancement.
  arXiv  Detail & Related papers  (2024-05-10T09:18:17Z)
• Learned Scalable Video Coding For Humans and Machines [4.14360329494344]
  We introduce an end-to-end learnable video task in its base layer, while its enhancement layer, together with the base layer, supports input reconstruction for human viewing. Our framework outperforms both state-of-the-art learned and conventional video codecs in its base layer, while maintaining comparable performance on the human vision task in its enhancement layer.
  arXiv  Detail & Related papers  (2023-07-18T05:22:25Z)
• A Coding Framework and Benchmark towards Low-Bitrate Video Understanding [63.05385140193666]
  We propose a traditional-neural mixed coding framework that takes advantage of both traditional codecs and neural networks (NNs) The framework is optimized by ensuring that a transportation-efficient semantic representation of the video is preserved. We build a low-bitrate video understanding benchmark with three downstream tasks on eight datasets, demonstrating the notable superiority of our approach.
  arXiv  Detail & Related papers  (2022-02-06T16:29:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.