arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.10335cs.CVcs.LGeess.IVeess.SP
收藏

edge-SR:大众的超分辨率

edge-SR: Super-Resolution For The Masses

BOE Technology Group Co., Ltd.(京东方科技集团股份有限公司)

Pablo Navarrete Michelini, Yunhua Lu, Xingqun Jiang

摘要:

经典的图像缩放(例如双三次)可以被视为一个卷积层和一个放大滤波器。其实现在所有显示器和图像处理软件中普遍存在。在过去的十年中,深度学习系统被引入用于图像超分辨率(SR)任务,使用多个卷积层和大量过滤器。这些方法已经接管了升级任务的图像质量基准。是否有可能在显示面板、平板电脑、膝上计算机等边缘设备上用深度学习架构取代经典的升级器?一方面,目前Edge-AI芯片的趋势显示出这一方向的光明前景,可以有效运行深度学习任务的硬件正在快速发展。另一方面,在镜像SR中,只有少数架构将极限推到了可以在边缘设备上实时运行的极小尺寸。我们探索这个问题的可能解决方案,旨在填补经典升级器和小型深度学习配置之间的空白。作为从经典到深度学习升级的过渡,我们提出了边缘SR(eSR),这是一组使用可解释机制来升级图像的单层架构。当然,单层架构无法达到深度学习系统的质量。然而,我们发现,对于高速要求,eSR在权衡图像质量和运行时性能方面变得更好。填补经典和深度学习架构之间的图像升级差距对于大规模采用这项技术至关重要。同样重要的是要有一个可解释的系统,可以揭示解决这个问题的内在策略,并指导我们未来的改进和更好地理解更大的网络。

英文摘要:

Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On one hand, the current trend in Edge-AI chips shows a promising future in this direction, with rapid development of hardware that can run deep-learning tasks efficiently. On the other hand, in image SR only few architectures have pushed the limit to extreme small sizes that can actually run on edge devices at real-time. We explore possible solutions to this problem with the aim to fill the gap between classic upscalers and small deep learning configurations. As a transition from classic to deep-learning upscaling we propose edge-SR (eSR), a set of one-layer architectures that use interpretable mechanisms to upscale images. Certainly, a one-layer architecture cannot reach the quality of deep learning systems. Nevertheless, we find that for high speed requirements, eSR becomes better at trading-off image quality and runtime performance. Filling the gap between classic and deep-learning architectures for image upscaling is critical for massive adoption of this technology. It is equally important to have an interpretable system that can reveal the inner strategies to solve this problem and guide us to future improvements and better understanding of larger networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑