VQAThinker: 通过强化学习探索通用且可解释的视频质量评估
VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
AI总结：
VQAThinker通过强化学习方法，结合大模型和规则引导算法，提升视频质量评估的泛化能力和可解释性。
摘要：
视频质量评估（VQA）旨在客观量化与人类视觉感知一致的感知质量退化。尽管近年来取得了进展，现有的VQA模型仍然存在两个关键限制：对分布外（OOD）视频的泛化能力差和可解释性有限，这限制了它们在现实世界中的应用。为了解决这些挑战，我们提出了VQAThinker，一个基于推理的VQA框架，利用大多模态模型（LMMs）和强化学习，共同建模视频质量理解和评分，模拟人类感知决策过程。具体而言，我们采用了组相对策略优化（GRPO），一种规则引导的强化学习算法，能够在评分级监督下对视频质量进行推理，并引入了三个专门针对VQA的奖励：（1）一个呈钟形的回归奖励，当预测误差减小时迅速增加，接近地面真实时逐渐变得不敏感；（2）一个成对排名奖励，引导模型正确确定视频对之间的相对质量；（3）一个时间一致性奖励，鼓励模型更倾向于选择时间一致的视频而非其扰动版本。大量实验表明，VQAThinker在域内和域外VQA基准上均实现了最先进的性能，显示出对视频质量评分的强泛化能力。此外，对视频质量理解任务的评估验证了其在失真归因和质量描述方面优于现有可解释VQA模型和LMMs。这些发现表明，强化学习为仅通过评分级监督构建通用且可解释的VQA模型提供了一条有效途径。
英文摘要：
Video quality assessment (VQA) aims to objectively quantify perceptual quality degradation in alignment with human visual perception. Despite recent advances, existing VQA models still suffer from two critical limitations: \textit{poor generalization to out-of-distribution (OOD) videos} and \textit{limited explainability}, which restrict their applicability in real-world scenarios. To address these challenges, we propose \textbf{VQAThinker}, a reasoning-based VQA framework that leverages large multimodal models (LMMs) with reinforcement learning to jointly model video quality understanding and scoring, emulating human perceptual decision-making. Specifically, we adopt group relative policy optimization (GRPO), a rule-guided reinforcement learning algorithm that enables reasoning over video quality under score-level supervision, and introduce three VQA-specific rewards: (1) a \textbf{bell-shaped regression reward} that increases rapidly as the prediction error decreases and becomes progressively less sensitive near the ground truth; (2) a \textbf{pairwise ranking reward} that guides the model to correctly determine the relative quality between video pairs; and (3) a \textbf{temporal consistency reward} that encourages the model to prefer temporally coherent videos over their perturbed counterparts. Extensive experiments demonstrate that VQAThinker achieves state-of-the-art performance on both in-domain and OOD VQA benchmarks, showing strong generalization for video quality scoring. Furthermore, evaluations on video quality understanding tasks validate its superiority in distortion attribution and quality description compared to existing explainable VQA models and LMMs. These findings demonstrate that reinforcement learning offers an effective pathway toward building generalizable and explainable VQA models solely with score-level supervision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
