论文标题
移动设备上现实世界图像的实时超分辨率
Real-Time Super-Resolution for Real-World Images on Mobile Devices
论文作者
论文摘要
图像超分辨率（ISR），旨在从相应的低分辨率（LR）对应物中恢复高分辨率（HR）图像。尽管ISR的最新进展非常出色。但是，由于最近的大多数方法都是基于深度学习的，因此它们在计算上太密集了，无法部署在边缘设备上。此外，这些方法在实际场景中始终失败，因为它们中的大多数都采用了简单的固定“理想”双音调下采样内核，从高质量的图像中构建LR/HR训练对，可能会失去与频率相关的细节的跟踪。在这项工作中，提出了移动设备上实时ISR的方法，该方法能够在现实世界中处理广泛的降级。对传统超分辨率数据集（Set5，Set14，BSD100，Urban100，Manga109，Div2k）和带有各种降级的现实世界图像进行了广泛的实验，这表明我们的方法表明，我们的方法表现出了较高的图像，从而超过了较高的PSNR和SSSIM和SSSIM，较低的噪音，较低的噪音，更低的视觉质量。最重要的是，我们的方法可以在移动设备或边缘设备上实现实时性能。
Image Super-Resolution (ISR), which aims at recovering High-Resolution (HR) images from the corresponding Low-Resolution (LR) counterparts. Although recent progress in ISR has been remarkable. However, they are way too computationally intensive to be deployed on edge devices, since most of the recent approaches are deep learning-based. Besides, these methods always fail in real-world scenes, since most of them adopt a simple fixed "ideal" bicubic downsampling kernel from high-quality images to construct LR/HR training pairs which may lose track of frequency-related details. In this work, an approach for real-time ISR on mobile devices is presented, which is able to deal with a wide range of degradations in real-world scenarios. Extensive experiments on traditional super-resolution datasets (Set5, Set14, BSD100, Urban100, Manga109, DIV2K) and real-world images with a variety of degradations demonstrate that our method outperforms the state-of-art methods, resulting in higher PSNR and SSIM, lower noise and better visual quality. Most importantly, our method achieves real-time performance on mobile or edge devices.
