RL-ScanIQA：强化学习扫描路径用于盲360度图像质量评估
RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360deg Image Quality Assessment
将扫描路径生成与质量评估统一为端到端强化学习框架，利用PPO训练策略网络接收质量反馈，为视觉任务中模拟人类观看行为提供了可复用的范式。
原文依据 RL-ScanIQA optimize a PPO-trained scanpath policy and a quality assessor, where the policy receives quality-driven feedback to learn task-relevant viewing strategies.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论盲360度图像质量评估（IQA）旨在在没有原始参考的情况下预测全景图像的感知质量。与传统平面图像不同，沉浸式环境中的360度内容将观看者限制在任意时刻的有限视口内，使得观看行为对质量感知至关重要。尽管现有的基于扫描路径的方法试图通过近似人类“先观看后评分”范式来建模观看行为，但它们将扫描路径生成和质量评估视为独立步骤，阻碍了端到端优化和任务对齐的探索。为解决这一局限，我们提出RL-ScanIQA，一种用于盲360度IQA的强化学习框架。RL-ScanIQA优化一个PPO训练的扫描路径策略和一个质量评估器，其中策略接收质量驱动的反馈以学习任务相关的观看策略。为提高训练稳定性并防止模式崩溃，我们设计了多级奖励，包括扫描路径多样性和赤道偏置先验。我们进一步通过失真空间增强以及保持图像内和图像间质量排序的秩一致性损失来提升跨数据集鲁棒性。在三个基准上的大量实验表明，RL-ScanIQA在数据集内性能和跨数据集泛化方面均取得优越表现。
英文原文摘要 1325 字符
Blind 360deg image quality assessment (IQA) aims to predict perceptual quality for panoramic images without a pristine reference. Unlike conventional planar images, 360deg content in immersive environments restricts viewers to a limited viewport at any moment, making viewing behaviors critical to quality perception. Although existing scanpath-based approaches have attempted to model viewing behaviors by approximating the human view-then-rate paradigm, they treat scanpath generation and quality assessment as separate steps, preventing end-to-end optimization and task-aligned exploration. To address this limitation, we propose RL-ScanIQA, a reinforcement-learned framework for blind 360deg IQA. RL-ScanIQA optimize a PPO-trained scanpath policy and a quality assessor, where the policy receives quality-driven feedback to learn task-relevant viewing strategies. To improve training stability and prevent mode collapse, we design multi-level rewards, including scanpath diversity and equator-biased priors. We further boost cross-dataset robustness using distortion-space augmentation together with rank-consistent losses that preserve intra-image and inter-image quality orderings. Extensive experiments on three benchmarks show that RL-ScanIQA achieves superior in-dataset performance and cross-dataset generalization.