论文标题
MSSNET：用于单图形的多尺度阶段网络
MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
论文作者
论文摘要
深度学习之前，大多数传统的单一图像灭绝方法都采用了一种粗到精细的方案，该方案以粗略的比例估算了锋利的图像，并逐渐在更细的尺度上完善了图像。虽然该方案也已采用了几种基于深度学习的方法，但最近引入了许多单一尺度方法，在质量和计算时间上都表现出了比以前的粗到精细方法出色的性能。在本文中，我们重新审视了粗到精细的方案，并分析了以前的粗到精细方法的缺陷，从而降低了其性能。基于分析，我们提出了多尺度阶段网络（MSSNET），这是一种基于深度学习的新型方法，用于单个图像脱布，将我们的补救措施采用到缺陷中。具体而言，MSSNET采用了三个新颖的技术组件：反映模糊量表的阶段配置，尺度间的信息传播方案和基于像素shuffle的多尺度方案。我们的实验表明，MSSNET在质量，网络大小和计算时间方面实现了最先进的性能。
Most of traditional single image deblurring methods before deep learning adopt a coarse-to-fine scheme that estimates a sharp image at a coarse scale and progressively refines it at finer scales. While this scheme has also been adopted to several deep learning-based approaches, recently a number of single-scale approaches have been introduced showing superior performance to previous coarse-to-fine approaches both in quality and computation time. In this paper, we revisit the coarse-to-fine scheme, and analyze defects of previous coarse-to-fine approaches that degrade their performance. Based on the analysis, we propose Multi-Scale-Stage Network (MSSNet), a novel deep learning-based approach to single image deblurring that adopts our remedies to the defects. Specifically, MSSNet adopts three novel technical components: stage configuration reflecting blur scales, an inter-scale information propagation scheme, and a pixel-shuffle-based multi-scale scheme. Our experiments show that MSSNet achieves the state-of-the-art performance in terms of quality, network size, and computation time.
