mlsanityData to 7 Oct 2026

SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation

arXiv 2605.14847 ↗First posted 14 May 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Modern image super-resolution methods generate detailed, visually appealing results, but they often introduce visual artifacts: unnatural patterns and texture distortions that degrade perceived quality. These defects vary widely in perceptual impact--some are barely noticeable, while others are highly disturbing--yet existing detection methods treat them equally. We propose artifact prominence as an evaluative target, defined as the fraction of viewers who judge a highlighted region to contain a noticeable artifact. We design a crowdsourced annotation protocol and construct SR-Prominence, a dataset suite containing 3,935 artifact masks from DeSRA, Open Images, Urban100, and a realistic no-ground-truth Urban100-HR setting, annotated with prominence. Re-annotating DeSRA reveals that 48.2% of its in-lab binary artifacts are not noticed by a majority of viewers. Across the suite, we audit SR artifact detectors, image-quality metrics, and SR methods. We find that classical full-reference metrics, especially SSIM and DISTS, provide surprisingly strong localized prominence signals, whereas no-reference IQA methods and specialized artifact detectors often fail to generalize across datasets and reference settings. SR-Prominence is released with an objective scoring protocol that allows new metrics to be benchmarked on our suite without further crowdsourcing. Together, the data and protocols enable SR artifact evaluation to move from binary defect presence toward perceptual impact. SR-Prominence is available at https://huggingface.co/datasets/imolodetskikh/sr-artifact-prominence.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

26 of 37 references.

References · 26

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  5. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  7. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  8. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  9. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  10. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  11. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  12. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
14 more
  1. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  2. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  3. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  4. 2023Rich Human Feedback for Text-to-Image Generationcited by 139
  5. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  6. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  7. 2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
  8. 2023Perceptual Artifacts Localization for Image Synthesis Taskscited by 43
  9. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  10. 2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
  11. 2023Swift Parameter-free Attention Network for Efficient Super-Resolutioncited by 24
  12. 2021ERQA: Edge-Restoration Quality Assessment for Video Super-Resolutioncited by 14
  13. 2025Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolutioncited by 5
  14. 2024JPEG AI Image Compression Visual Artifacts: Detection Methods and Datasetcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SR-Ground: Image Quality Grounding for Super-Resolved Contentcited by 0