cGAN-Based Manga Colorization Using a Single Training Image
cGAN-Based Manga Colorization Using a Single Training Image
复制标题
DOI：
10.1109/icdar.2017.295
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Paulina Hensman;K. Aizawa
中科院分区：
文献类型：
--
作者：
Paulina Hensman;K. Aizawa
被称为漫画的日本漫画形式在世界各地很受欢迎。它传统上是用黑白制作的，彩色化既耗时又昂贵。自动上色方法通常依赖于漫画中不存在的灰度值。此外，由于版权保护，可供培训的彩色漫画很少。提出了一种基于条件生成对抗网络的漫画彩色化方法。与以往使用成百上千幅训练图像的cGAN方法不同，我们的方法只需要一幅彩色参考图像进行训练，避免了对大数据集的需要。使用cGAN为漫画上色可能会产生带有瑕疵的模糊效果，并且分辨率有限。因此，我们还提出了一种分割和颜色校正的方法来缓解这些问题。最终的结果是清晰、清晰和高分辨率的，并保持了角色的原始配色方案。
The Japanese comic format known as Manga is popular all over the world. It is traditionally produced in black and white, and colorization is time consuming and costly. Automatic colorization methods generally rely on greyscale values, which are not present in manga. Furthermore, due to copyright protection, colorized manga available for training is scarce. We propose a manga colorization method based on conditional Generative Adversarial Networks (cGAN). Unlike previous cGAN approaches that use many hundreds or thousands of training images, our method requires only a single colorized reference image for training, avoiding the need of a large dataset. Colorizing manga using cGANs can produce blurry results with artifacts, and the resolution is limited. We therefore also propose a method of segmentation and color-correction to mitigate these issues. The final results are sharp, clear, and in high resolution, and stay true to the character's original color scheme.