Image colorization is the process of assigning different RGB values to each pixel of a given grayscale image to obtain the corresponding colorized image. In this work, we propose a new automatic image colorization method based on the modified cycle-consistent generative adversarial network (CycleGAN). This method can generate a natural color image with only one given gray image without reference image or manual interaction. In the proposed method, we first modify the original network structure by combining a u-shaped network with a skip connection to improve the ability of feature representation in image colorization. Meanwhile, we design a compounded loss function to measure the errors between the ground-truth image and the predicted result to improve the authenticity and naturalness of the colorized image; further, we also add the detail loss function to ensure that the details of the generated color and grayscale images are substantially similar. Finally, the performance of the proposed model is verified on different datasets. Experiments show that our method can generate more realistic color images when compared to other methods.

图像着色是将不同的RGB值分配给给定灰度图像的每个像素以获得相应的彩色图像的过程。在这项工作中，我们提出了一种基于改进的周期一致的生成对抗网络（CycleGAN）的新的自动图像着色方法。该方法可以生成仅具有一个给定的灰度图像的自然彩色图像，而无需参考图像或手动交互。在提出的方法中，我们首先通过将u型网络与跳过连接相结合来修改原始网络结构，以提高图像着色中特征表示的能力。同时，我们设计了一种复合损失函数来测量真实图像与预测结果之间的误差，以提高彩色图像的真实性和自然性。更多，我们还添加了细节损失功能，以确保生成的彩色和灰度图像的细节基本相似。最后，在不同的数据集上验证了所提出模型的性能。实验表明，与其他方法相比，我们的方法可以生成更逼真的彩色图像。