论文标题
无监督的信息理论感知质量指标
An Unsupervised Information-Theoretic Perceptual Quality Metric
论文作者
论文摘要
事实证明，人类感知模型的建设具有挑战性。由于其简单性和速度，手工设计的模型（例如MS-SSIM）仍然是人类图像质量判断的流行预测指标。最近的现代深度学习方法可以更好地表现，但是它们依靠有监督的数据来收集的昂贵：大量的类标签，例如ImageNet，图像质量评级或两者兼而有之。我们将信息理论目标功能的最新进展与由人类视觉系统的生理学和无监督的视频框架培训所告知的计算架构，从而产生了我们的感知信息指标（PIM）。我们表明，PIM在最近和挑战性的Bapps图像质量评估数据集上与受到监督指标具有竞争力，并且在预测CLIC 2020中图像压缩方法的排名方面都超越了它们。我们还使用Imagenet-C数据集执行定性实验，并确定PIM与建筑细节相关。
Tractable models of human perception have proved to be challenging to build. Hand-designed models such as MS-SSIM remain popular predictors of human image quality judgements due to their simplicity and speed. Recent modern deep learning approaches can perform better, but they rely on supervised data which can be costly to gather: large sets of class labels such as ImageNet, image quality ratings, or both. We combine recent advances in information-theoretic objective functions with a computational architecture informed by the physiology of the human visual system and unsupervised training on pairs of video frames, yielding our Perceptual Information Metric (PIM). We show that PIM is competitive with supervised metrics on the recent and challenging BAPPS image quality assessment dataset and outperforms them in predicting the ranking of image compression methods in CLIC 2020. We also perform qualitative experiments using the ImageNet-C dataset, and establish that PIM is robust with respect to architectural details.
