按人眼感知重要性检测图像超分中的视觉瑕疵，更精准。
Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution
- 根据人眼感知重要性区分瑕疵严重程度，而非简单二分类。
- 构建含1302例的标注数据集，发现近半数瑕疵几乎无人察觉。
- 轻量级模型生成显著性热图，可指导模型优化减少干扰瑕疵。
生成式单图像超分辨率（SISR）发展迅速，但顶尖模型仍会产生视觉瑕疵：不自然的图案和纹理扭曲，降低观感质量。这些缺陷对人类感知的影响差异巨大——有些几乎不可见，有些却极为刺眼，但现有检测方法将其视为均质缺陷。本文提出以人眼感知显著性来刻画瑕疵，而非统一判断。我们构建了一个包含11种SISR方法产生的1302个瑕疵样本的新数据集，并为DeSRA数据集中593个已有瑕疵提供人群标注的显著性评分，发现其中48%被多数观察者忽略。基于该数据，训练出一个轻量级回归器，可生成空间显著性热图。实验表明，该方法优于现有检测器，并有效指导SR模型微调以抑制瑕疵。代码与数据集已公开于https://tinyurl.com/2u9zxtyh。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。