Image Colorization with Generative Adversarial Networks
This work addresses image restoration for applications like aged or degraded images, but it is incremental as it builds on existing GAN methods.
The paper tackles the ill-posed problem of automatic image colorization by using a conditional DCGAN to generalize the procedure, extend to high-resolution images, and improve training stability, comparing results with traditional deep neural networks on datasets like CIFAR-10 and Places365.
Over the last decade, the process of automatic image colorization has been of significant interest for several application areas including restoration of aged or degraded images. This problem is highly ill-posed due to the large degrees of freedom during the assignment of color information. Many of the recent developments in automatic colorization involve images that contain a common theme or require highly processed data such as semantic maps as input. In our approach, we attempt to fully generalize the colorization procedure using a conditional Deep Convolutional Generative Adversarial Network (DCGAN), extend current methods to high-resolution images and suggest training strategies that speed up the process and greatly stabilize it. The network is trained over datasets that are publicly available such as CIFAR-10 and Places365. The results of the generative model and traditional deep neural networks are compared.