End-to-End Conditional GAN-based Architectures for Image Colourisation
arXiv:1908.09873
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.
arXiv commentIEEE 21st International Workshop on Multimedia Signal Processing, 27-29 Sept 2019, Kuala Lumpur, Malaysia
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Spectral Normalization for Generative Adversarial Networks
- Instance Normalization: The Missing Ingredient for Fast Stylization
- NIPS 2016 Tutorial: Generative Adversarial Networks
- Real-Time User-Guided Image Colorization with Learned Deep Priors