arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1608.00367cs.CV
收藏

加速超分辨率卷积神经网络

Accelerating the Super-Resolution Convolutional Neural Network

The Chinese University of Hong Kong(香港中文大学)

Chao Dong, Chen Change Loy, Xiaoou Tang

摘要:

超分辨率卷积神经网络(SRCNN)作为一种成功应用于图像超分辨率(SR)的深度模型,在速度和恢复质量上都表现出了优于以往手工模型的性能。然而,高计算成本仍然阻碍了它的实际使用,需要实时性能(24 fps)。本文旨在加速当前的SRCNN,并提出了一种紧凑的沙漏形CNN结构,以实现更快更好的SR。我们主要从三个方面重新设计了SRCNN结构。首先,我们在网络的末端引入一个反卷积层,然后直接从原始低分辨率图像(没有插值)到高分辨率图像的映射。其次,我们重新制定映射层,在映射之前缩小输入特征维度,之后再扩大。第三,我们采用更小的过滤器大小,但更多的映射层。该模型实现了超过40倍的速度,甚至更优越的恢复质量。此外,我们提出的参数设置,可以实现通用CPU的实时性能,同时仍然保持良好的性能。针对不同尺度因子的快速训练和测试,提出了相应的迁移策略。

英文摘要:

As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we aim at accelerating the current SRCNN, and propose a compact hourglass-shape CNN structure for faster and better SR. We re-design the SRCNN structure mainly in three aspects. First, we introduce a deconvolution layer at the end of the network, then the mapping is learned directly from the original low-resolution image (without interpolation) to the high-resolution one. Second, we reformulate the mapping layer by shrinking the input feature dimension before mapping and expanding back afterwards. Third, we adopt smaller filter sizes but more mapping layers. The proposed model achieves a speed up of more than 40 times with even superior restoration quality. Further, we present the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. A corresponding transfer strategy is also proposed for fast training and testing across different upscaling factors.

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。

↑