DISRQAD: Diffusion Image Super-Resolution Quality Assessment Dataset and Benchmark

Researchers introduced DISRQAD, a subjective-quality dataset and diagnostic benchmark containing mean opinion scores for 14,000 super-resolution outputs from ten diffusion and four non-diffusion methods across four low-resolution degradation conditions and x2/x4 upscaling. Evaluating 51 standard full-reference and no-reference metric configurations plus 11 adapted variants, the team found agreement with human scores 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. A pruned and distilled Q-ReAlign-mini student reaches 0.496 SRCC on diffusion SR, and the authors state DISRQAD measures perceived output quality rather than faithfulness to the input.

arXiv:2610.09077v1 Announce Type: new 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.