一类新的清晰度感知指标的主观研究
A Subjective Study on a New Sharpness Informed Class of Metrics
浏览论文内容
中文总结 AI 辅助
针对DNN去模糊模型缺乏明确针对清晰度的损失函数的问题，开展主观研究，构建含均匀清晰度增量及DMOS的数据集，提出SI-IQA指标，SI-PSNR表现更优，清晰度感知复合损失恢复的图像在67%二值化比较中更受偏好。
中文摘要 AI 辅助
深度神经网络（DNN）去模糊架构中的感知损失函数可提升恢复图像的整体质量，但很少有研究明确针对恢复图像的清晰度。我们采用四协议方法对使用明确针对清晰度的损失函数训练的模型和未使用该损失函数训练的模型进行主观研究，探究偏好的清晰度水平及其对图像质量的影响。我们引入了一个具有均匀清晰度增量的新图像数据集，以及差分平均意见得分（DMOS）。此外，我们提出了一类新的清晰度感知（SI）图像质量评估（IQA）指标，该指标可适当惩罚过度锐化。我们的新SI-PSNR指标在IQA基准数据集上的相关统计方面优于所有其他PSNR变体。结果表明，平均而言，使用清晰度感知复合损失恢复的图像在67%的二值化比较中更受偏好，而未明确针对清晰度的损失函数则不然。
英文摘要
Perceptual loss functions in Deep Neural Network (DNN) deblurring architectures improve the overall quality of restored images. However, few focus on explicitly targeting sharpness in the restorations. We conduct a subjective study of models trained with and without losses which explicitly target sharpness using a four-protocol approach, exploring preferred sharpness levels and effects on image quality. We introduce a novel dataset of images with uniform sharpness increments along with Difference Mean Opinion Scores (DMOS). Additionally, we propose a novel class of Sharpness Informed (SI) Image Quality Assessment (IQA) metrics which properly penalize over-sharpening. Our new SI-PSNR metric outperforms all other PSNR variants in terms of correlation statistics on IQA benchmarking datasets. We show that, on average, images restored using a sharpness-aware composite loss are preferred in 67% of binarized comparisons, as opposed to losses that do not explicitly target sharpness.
发表机构
- Trinity College Dublin（都柏林圣三一学院）
机构由 AI 辅助整理，请以论文原文为准。
