Image Colorization with Generative Adversarial Networks

TL;DR

This paper presents a conditional DCGAN approach for automatic image colorization that generalizes the process, handles high-resolution images, and improves training stability, with evaluations on CIFAR-10 and Places365 datasets.

Contribution

It introduces a fully generalizable colorization method using conditional DCGANs, extending to high-resolution images and proposing training strategies for stability and speed.

Findings

The proposed method effectively colorizes images across various datasets.

It outperforms traditional deep neural networks in colorization quality.

The approach stabilizes training and accelerates convergence.

Abstract

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.