Metraipolis › archive › dc_7ba63ddf44b1

DISRQAD: Diffusion Image Super-Resolution Quality Assessment Dataset and Benchmark — arXiv:2610.09077

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09077
License (as archived)
CC0-1.0
Archived
2026-10-08T12:46:55.209Z
SHA-256 of the archived text
b464246457d1e07eb43866ae852f88ae687ad3272795ab84db9009032a053eba
Stable URL of this page
https://metraipolis.com/documento/dc_7ba63ddf44b1

How to cite

DISRQAD: Diffusion Image Super-Resolution Quality Assessment Dataset and Benchmark — arXiv:2610.09077 — arXiv (en), https://arxiv.org/abs/2610.09077 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ba63ddf44b1 (Metraipolis archive dc_7ba63ddf44b1, sha256 b464246457d1e07eb43866ae852f88ae687ad3272795ab84db9009032a053eba)
BibTeX
@misc{dc7ba63ddf44b1,
  title = {DISRQAD: Diffusion Image Super-Resolution Quality Assessment Dataset and Benchmark — arXiv:2610.09077},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09077},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ba63ddf44b1; sha256 b464246457d1e07eb43866ae852f88ae687ad3272795ab84db9009032a053eba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09077. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09077 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:15.299Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).