A Learned Representation of Artist-Specific Colourisation

Nanne van Noord, Eric Postma; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2907-2915


The colours used in a painting are determined by artists and the pigments at their disposal. Therefore, knowing who made the painting should help in determining which colours to hallucinate when given a colourless version of the painting. The main aim of this paper is to determine if we can create a colourisation model for paintings which generates artist-specific colourisations. Building on earlier work on natural-image colourisation, we propose a model capable of producing colourisations of paintings by incorporating a conditional normalisation scheme, i.e., conditional instance normalisation. The results indicate that a conditional normalisation scheme is beneficial to the performance. We conclude that painting colourisation is feasible and benefits from being trained on a dataset of paintings and from applying a conditional normalisation scheme.

Related Material

author = {van Noord, Nanne and Postma, Eric},
title = {A Learned Representation of Artist-Specific Colourisation},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}