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

arXiv: https://arxiv.org/abs/1908.09873 · HTML: https://mlsanity.com/paper/1908.09873/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 8 of 8)

- [ZONE: Zero-Shot Instruction-Guided Local Editing](https://mlsanity.com/paper/2312.16794/) (2023)
- [CAFLOW: Conditional Autoregressive Flows](https://mlsanity.com/paper/2106.02531/) (2021)
- [Attention-based Stylisation for Exemplar Image Colourisation](https://mlsanity.com/paper/2105.01705/) (2021)
- [Improved CNN-based Learning of Interpolation Filters for Low-Complexity Inter Prediction in Video Coding](https://mlsanity.com/paper/2106.08936/) (2021)
- [Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding](https://mlsanity.com/paper/2102.04993/) (2021)
- [Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach](https://mlsanity.com/paper/2110.09170/) (2021)
- [Towards Transparent Application of Machine Learning in Video Processing](https://mlsanity.com/paper/2105.12700/) (2021)
- [Human vs Objective Evaluation of Colourisation Performance](https://mlsanity.com/paper/2204.05200/) (2022)

## Abstract (arXiv)

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.