Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks

TL;DR

This paper explores automatic image colorization using convolutional neural networks and generative adversarial networks, addressing the ill-posed problem by leveraging scene semantics and texture cues for more accurate color prediction.

Contribution

It introduces a novel approach combining CNNs and GANs for image colorization, improving upon prior regression-based methods by incorporating classification and adversarial learning.

Findings

Enhanced colorization quality demonstrated through experiments

Comparison shows improvements over traditional regression methods

Utilizes scene semantics for more realistic colors

Abstract

Image colorization, the task of adding colors to grayscale images, has been the focus of significant research efforts in computer vision in recent years for its various application areas such as color restoration and automatic animation colorization [15, 1]. The colorization problem is challenging as it is highly ill-posed with two out of three image dimensions lost, resulting in large degrees of freedom. However, semantics of the scene as well as the surface texture could provide important cues for colors: the sky is typically blue, the clouds are typically white and the grass is typically green, and there are huge amounts of training data available for learning such priors since any colored image could serve as a training data point [20]. Colorization is initially formulated as a regression task[5], which ignores the multi-modal nature of color prediction. In this project, we explore automatic image colorization via classification and adversarial learning. We will build our models on prior works, apply modifications for our specific scenario and make comparisons.