Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910019580067840 |
|---|---|
| author | Molodetskikh, Ivan Malyshev, Kirill Mirgaleev, Mark Zagainov, Nikita Bogatyrev, Evgeney Vatolin, Dmitriy |
| author_facet | Molodetskikh, Ivan Malyshev, Kirill Mirgaleev, Mark Zagainov, Nikita Bogatyrev, Evgeney Vatolin, Dmitriy |
| contents | Generative single-image super-resolution (SISR) is advancing rapidly, yet even state-of-the-art models produce 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 characterizing artifacts by their prominence to human observers rather than as uniform binary defects. We present a novel dataset of 1302 artifact examples from 11 SISR methods annotated with crowdsourced prominence scores, and provide prominence annotations for 593 existing artifacts from the DeSRA dataset, revealing that 48% of them go unnoticed by most viewers. Building on this data, we train a lightweight regressor that produces spatial prominence heatmaps. We demonstrate that our method outperforms existing detectors and effectively guides SR model fine-tuning for artifact suppression. Our dataset and code are available at https://tinyurl.com/2u9zxtyh. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution Molodetskikh, Ivan Malyshev, Kirill Mirgaleev, Mark Zagainov, Nikita Bogatyrev, Evgeney Vatolin, Dmitriy Computer Vision and Pattern Recognition Machine Learning Generative single-image super-resolution (SISR) is advancing rapidly, yet even state-of-the-art models produce 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 characterizing artifacts by their prominence to human observers rather than as uniform binary defects. We present a novel dataset of 1302 artifact examples from 11 SISR methods annotated with crowdsourced prominence scores, and provide prominence annotations for 593 existing artifacts from the DeSRA dataset, revealing that 48% of them go unnoticed by most viewers. Building on this data, we train a lightweight regressor that produces spatial prominence heatmaps. We demonstrate that our method outperforms existing detectors and effectively guides SR model fine-tuning for artifact suppression. Our dataset and code are available at https://tinyurl.com/2u9zxtyh. |
| title | Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2510.16752 |