研究人员开发了 SR-Prominence，这是一个用于评估图像超分辨率中伪影的新数据集和协议。这种众包方法衡量“伪影突出度”，即注意到伪影的观看者百分比，超越了简单的二元检测。该数据集包含 3,935 个伪影掩码，并显示许多先前识别出的伪影并未被大多数观看者感知。研究结果表明，SSIM 和 DISTS 等传统指标为突出度提供了强烈的信号，而专门的伪影检测器通常缺乏通用性。 AI
影响 为评估 AI 生成图像的感知质量提供了一个新的基准，有可能改进未来的图像增强模型。
排序理由 在 arXiv 上发布了一篇新的学术论文和数据集。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
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, w…
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, w…