End-to-End Conditional GAN-based Architectures for Image Colourisation

TL;DR

This paper presents an end-to-end CNN-based conditional GAN architecture for image colourisation, improving colourfulness and generalisation on large datasets through training stability enhancements and normalization techniques.

Contribution

It introduces a novel GAN-based colourisation method with integrated normalization layers and training stability improvements, advancing the state-of-the-art in automatic image colourisation.

Findings

Achieved better colourfulness in colourised images.

Demonstrated improved generalisation on large multi-class datasets.

Outperformed existing GAN-based colourisation methods.

Abstract

In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image. Observing that existing colourisation methods sometimes exhibit a lack of colourfulness, this paper proposes a method to improve colourisation results. In particular, the method uses Generative Adversarial Neural Networks (GANs) and focuses on improvement of training stability to enable better generalisation in large multi-class image datasets. Additionally, the integration of instance and batch normalisation layers in both generator and discriminator is introduced to the popular U-Net architecture, boosting the network capabilities to generalise the style changes of the content. The method has been tested using the ILSVRC 2012 dataset, achieving improved automatic colourisation results compared to other methods based on GANs.