Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution
This work addresses the issue of varying perceptual impact of artifacts in super-resolution for researchers and practitioners, offering a dataset and tool for prominence-aware evaluation, though it is incremental in focusing on detection rather than mitigation.
The paper tackles the problem of artifacts in generative image super-resolution by introducing a dataset of 1302 artifact examples with crowdsourced prominence scores and a lightweight regressor that outperforms existing methods in detecting prominent artifacts.
Generative image super-resolution (SR) is rapidly advancing in visual quality and detail restoration. As the capacity of SR models expands, however, so does their tendency to produce artifacts: incorrect, visually disturbing details that reduce perceived quality. Crucially, their perceptual impact varies: some artifacts are barely noticeable while others strongly degrade the image. We argue that artifacts should be characterized by their prominence to human observers rather than treated as uniform binary defects. Motivated by this, we present a novel dataset of 1302 artifact examples from 11 contemporary image-SR methods, where each artifact is paired with a crowdsourced prominence score. Building on this dataset, we train a lightweight regressor that produces spatial prominence heatmaps and outperforms existing methods at detecting prominent artifacts. We release the dataset and code to facilitate prominence-aware evaluation and mitigation of SR artifacts.