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

arXiv: https://arxiv.org/abs/2610.09077 · HTML: https://mlsanity.com/paper/2610.09077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 8 of its 80 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2403.11176/) (2024)
- [Bridging the Perception Gap in Image Super-Resolution Evaluation](https://mlsanity.com/paper/2503.13074/) (2025)
- [SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation](https://mlsanity.com/paper/2605.14847/) (2026)
- [SR-Ground: Image Quality Grounding for Super-Resolved Content](https://mlsanity.com/paper/2605.21244/) (2026)
- [How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?](https://mlsanity.com/paper/2605.25940/) (2026)
- [LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models](https://mlsanity.com/paper/2606.02535/) (2026)

## Abstract (arXiv)

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.