论文标题
块状散装：一种高分辨率快速转移的方法，内存有限
Block Shuffle: A Method for High-resolution Fast Style Transfer with Limited Memory
论文作者
论文摘要
快速样式转移是一系列神经风格转移算法，它们使用馈送前向神经网络呈现输入图像。由于输出层的高维度，这些网络需要大量内存才能进行计算。因此，对于高分辨率图像，大多数移动设备和个人计算机无法对它们进行样式化，这极大地限制了快速传输的应用程序方案。目前，现有的两个解决方案正在购买更多的内存并使用基于羽毛的方法，但前者需要额外的成本，而后者的图像质量较差。为了解决这个问题，我们提出了一种名为\ emph {block shuffle}的新型图像合成方法，该方法将具有高内存消耗的单个任务转换为具有低内存消耗的多个子任务。此方法可以充当快速样式传输的插件，而无需对网络体系结构进行任何修改。我们将GitHub上最受欢迎的快速传输存储库用作基线。实验表明，我们方法生成的高分辨率图像的质量比基于羽毛的方法的质量更好。尽管我们的方法比基线要慢，但它可以对具有有限内存的高分辨率图像进行风格化，这对于基线而言是不可能的。代码和型号将在\ url {https://github.com/czczup/block-shuffle}上提供。
Fast Style Transfer is a series of Neural Style Transfer algorithms that use feed-forward neural networks to render input images. Because of the high dimension of the output layer, these networks require much memory for computation. Therefore, for high-resolution images, most mobile devices and personal computers cannot stylize them, which greatly limits the application scenarios of Fast Style Transfer. At present, the two existing solutions are purchasing more memory and using the feathering-based method, but the former requires additional cost, and the latter has poor image quality. To solve this problem, we propose a novel image synthesis method named \emph{block shuffle}, which converts a single task with high memory consumption to multiple subtasks with low memory consumption. This method can act as a plug-in for Fast Style Transfer without any modification to the network architecture. We use the most popular Fast Style Transfer repository on GitHub as the baseline. Experiments show that the quality of high-resolution images generated by our method is better than that of the feathering-based method. Although our method is an order of magnitude slower than the baseline, it can stylize high-resolution images with limited memory, which is impossible with the baseline. The code and models will be made available on \url{https://github.com/czczup/block-shuffle}.
