摘要：基于扩散模型的图像超分辨率（SR）能够生成视觉上看似合理、但并无低分辨率输入支持的细节。我们提出 DISRQAD，这是一个面向这一场景的主观质量数据集与诊断基准。该数据集包含 10 种扩散方法和 4 种非扩散方法生成的 14,000 张 SR 输出的平均主观评分（MOS），覆盖四种低分辨率退化条件以及 x2/x4 放大倍率。我们评估了 51 种标准全参考和无参考指标配置，以及 11 种经适配的变体。指标与 MOS 的一致性在扩散输出上明显更弱：表现最强的标准无参考基线在扩散 SR 上仅达到 0.431 SRCC，而在非扩散 SR 上达到 0.813。作为基准使用的案例研究，经剪枝和蒸馏的 Q-ReAlign-mini 学生模型在扩散 SR 上达到 0.496 SRCC。DISRQAD 衡量的是感知输出质量，而非对输入的忠实度；它支持分析不同生成器家族及输入条件下的指标行为。我们的发现揭示了扩散式 SR 评估中的显著缺口，并为开发能够识别扩散模型特有伪影的质量模型提供了基础。

Abstract:Diffusion-based image super-resolution (SR) can create visually plausible detail that is not supported by the low-resolution input. We introduce DISRQAD, a subjective-quality dataset and diagnostic benchmark for this setting. It contains mean opinion scores (MOS) for 14,000 SR outputs from ten diffusion and four non-diffusion methods, spanning four low-resolution degradation conditions and x2/x4 upscaling. We evaluate 51 standard full-reference and no-reference metric configurations and 11 adapted variants. Agreement with MOS is substantially weaker on diffusion outputs: the strongest standard no-reference baseline reaches 0.431 SRCC on diffusion SR versus 0.813 on non-diffusion SR. As a case study in benchmark use, a pruned and distilled Q-ReAlign-mini student reaches 0.496 SRCC on diffusion SR. DISRQAD measures perceived output quality, not faithfulness to the input; it enables analysis of metric behavior across generator families and input conditions. Our findings reveal a substantial gap in the assessment of diffusion-based SR and provide a basis for developing quality models sensitive to diffusion-specific artifacts.