Colorization methods using deep neural networks have become a recent trend. However, most of them do not allow user inputs, or only allow limited user inputs (only global inputs or only local inputs), to control the output colorful images. The possible reason is that it's difficult to differentiate the influence of different kind of user inputs in network training. To solve this problem, we present a novel deep colorization method, which allows simultaneous global and local inputs to better control the output colorized images. The key step is to design an appropriate loss function that can differentiate the influence of input data, global inputs and local inputs. With this design, our method accepts no inputs, or global inputs, or local inputs, or both global and local inputs, which is not supported in previous deep colorization methods. In addition, we propose a global color theme recommendation system to help users determine global inputs. Experimental results shows that our methods can better control the colorized images and generate state-of-art results.

本文介绍了一种新的深度上色方法，它允许同时输入全局和局部输入来更好地控制输出的上色图像，并设计了适当的损失函数来区分输入数据、全局输入和局部输入的影响。此外，本文还提出了一个全局颜色主题推荐系统来帮助用户确定全局输入，实验结果显示我们的方法能够更好地控制上色图像并生成最先进的结果。

交互式深度上色与全局/局部输入同时进行