学习看哪里与如何判断：基于质量感知显著性的分辨率无关图像质量评价
Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
用 CLIP 多尺度定长 patch 采样保留原分辨率质量线索，并用轻量显著性估计器挑选少量信息 patch 再聚合打分，这套「先学看哪里、再判断质量」的预算自适应流程可直接迁移到超分/去噪等复原任务的质量评估与训练奖励。
原文依据 A lightweight Perceptual Importance Estimator then predicts IQA-specific importance maps to select a small set of informative patches
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无参考图像质量评价（NR IQA）近来受益于深度模型与多模态模型，但许多最先进系统仍至少违反一项基本要求：它们或通过激进缩放丢弃关键质量线索，或无法跨分辨率泛化，或无法在 MOS 尺度不一致的异构 IQA 数据集上联合训练，或需要过高的计算开销。我们提出 ReLIQS，一个用于分辨率无关的图像质量学习与显著性的模型，它分辨率无关、保留原始分辨率的质量线索、可从多项主观研究中学习，并保持计算高效与预算自适应。ReLIQS 是一种基于 CLIP 的多尺度图像块驱动架构，同时学习看哪里与如何判断质量。定长图像块在包括原始分辨率在内的多个分辨率上被采样，并用 CLIP 视觉骨干编码。随后一个轻量的感知重要性估计器预测 IQA 专用的重要性图，以挑选少量信息量大的图像块，一个质量方面模块将其嵌入聚合为单一图像级分数。在涵盖多种分辨率与失真的真实、合成与 AIGC 基准上，ReLIQS 以相当或更低的计算开销，比强 CNN、CLIP 与 MLLM 基线泛化得更好。
英文原文摘要 1356 字符
No-reference image quality assessment (NR IQA) has recently benefited from deep and multimodal models, yet many SOTA systems still violate at least one basic requirement: they either discard critical quality cues via aggressive resizing, fail to generalize across resolutions, cannot be jointly trained on heterogeneous IQA datasets with mismatched MOS scales, or require prohibitive computation. We present ReLIQS, a model for Resolution-agnostic Learning for Image Quality with Saliency, which is resolution-agnostic, preserves original-resolution quality cues, learns from multiple subjective studies, and remains computationally efficient and budget-adaptive. ReLIQS is a CLIP-based multiscale patch-driven architecture that learns both where to look and how to judge quality. Fixed-size patches are sampled across multiple resolutions, including the original resolution, and encoded with a CLIP vision backbone. A lightweight Perceptual Importance Estimator then predicts IQA-specific importance maps to select a small set of informative patches, and a Quality Aspect Module aggregates their embeddings into a single image-level score. Across authentic, synthetic, and AIGC benchmarks spanning diverse resolutions and distortions, ReLIQS generalizes better than strong CNN-, CLIP-, and MLLM-based baselines with matching or reduced computational cost.