Despite the great advances made on image super-resolution (ISR) during the last years, the performance has solely been evaluated perceptually. Thus, it is still unclear how useful ISR is to other vision tasks in practice. In this paper, we present the first comprehensive study and analysis of the usefulness of ISR for other vision applications. In particular, five ISR methods are evaluated on four popular vision tasks, namely edge detection, semantic image labeling, digit recognition, and face detection. We show that applying ISR to input images of other vision systems does improve the performance when the input images are of low-resolution. This is because the features and algorithms of current vision systems are designed and optimized for images of normal resolution. We also demonstrate that the standard perceptual evaluation criteria, such as PSNR and SSIM, correlate quite well with the usefulness of ISR methods to other vision tasks, but cannot measure it very accurately. We hope this work will inspire the community to evaluate ISR methods also in real vision applications, and to deploy ISR as a preprocessing component for systems of other vision tasks if the input data are of relatively low-resolution.

本论文研究并分析了使用图像超分辨率 (ISR) 技术在其它视觉应用中的可用性。作者对四种流行的视觉任务 - 边缘检测、语义图像分割、数字识别和场景识别 - 测试了六种 ISR 方法的表现，结果表明当其它视觉系统输入低分辨率的图像时，使用 ISR 技术能够提高它们的性能。还研究了四种标准的感知评估准则和 ISR 对视觉任务的可用性之间的相关性，发现它们之间存在一定的相关性，但感知准则仍不能作为 ISR 可用性的完全代理。本研究希望鼓励社区在研究 ISR 方法时注重实际应用，并在输入图像分辨率低的情况下将 ISR 作为其它视觉任务的预处理步骤。

图像超分辨率技术是否有益于其他视觉任务？