用渐进式强化学习教视觉语言模型理解AI生成视频质量
VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning
- 分三阶段训练：先学图像质量，再学时序特征，最后与生成模型联合优化
- 多维度奖励机制使评分在偏好对比、多维打分和自然视频评估中均领先
- 适合需要高质量视频生成反馈的AI研发者，尤其关注生成内容评估
近年来，文本到视频生成模型取得了显著进展。然而，由于泛化能力有限、缺乏时序感知、严重依赖大规模标注数据，且难以与生成模型有效交互，AI生成视频的质量评估仍具挑战。现有方法多采用监督微调视觉语言模型（VLMs），往往需大量标注数据，且理解与生成过程脱节。为此，我们提出VQ-Insight，一种新型推理式VLM框架，用于AIGC视频质量评估。其核心包括：(1) 渐进式视频质量学习策略，融合图像质量预热、任务特定时序学习及与视频生成模型的联合优化；(2) 设计多维度评分奖励、偏好对比奖励与时序建模奖励，提升评估的泛化性与专业性。大量实验表明，VQ-Insight在偏好对比、多维度评分和自然视频评分任务中持续优于当前最优基线，显著提升视频生成质量。
原文摘要 · Abstract (English)
Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited generalization, lack of temporal awareness, heavy reliance on large-scale annotated datasets, and the lack of effective interaction with generation models. Most current approaches rely on supervised finetuning of vision-language models (VLMs), which often require large-scale annotated datasets and tend to decouple understanding and generation. To address these shortcomings, we propose VQ-Insight, a novel reasoning-style VLM framework for AIGC video quality assessment. Our approach features: (1) a progressive video quality learning scheme that combines image quality warm-up, general task-specific temporal learning, and joint optimization with the video generation model; (2) the design of multi-dimension scoring rewards, preference comparison rewards, and temporal modeling rewards to enhance both generalization and specialization in video quality evaluation. Extensive experiments demonstrate that VQ-Insight consistently outperforms state-of-the-art baselines in preference comparison, multi-dimension scoring, and natural video scoring, bringing significant improvements for video generation tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。