Document Type
Article
Rights
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
Disciplines
2. ENGINEERING AND TECHNOLOGY
Abstract
Automatic colourisation is the function of inferring colour information from a grey-scale prior and then combining the colour with the grey-scale to form a colourised version of the image. We identify Spatial Coherence as a particular weakness in methods that use Convolutional Neural Networks for colourisation. Generated colours do not adhere to semantic edges and are not consistent within boundaries where we would expect uniform colour. Spatial Coherence, while often evident to the human eye, does not yet have an objective metric. We show, by segmentation of the combined ab channels of the CIEL*a*b* colour space, that a segmentation based on CNN colourisation is poor. We argue the need for the development of metrics to evaluate a colourisation’s performance on Spatial Coherence.
DOI
http://doi.org10.21427/n7td-0f30
Recommended Citation
Mullery, S., & Whelan, P. (2019). Spatial coherency in colourisation. i>IMVIP 2019: Irish Machine Vision & Image Processing, Technological University Dublin, Dublin, Ireland, August 28-30. doi:10.21427/n7td-0f30
Publication Details
IMVIP 2019: Irish Machine Vision & Image Processing, Technological University Dublin, Dublin, Ireland, August 28-30.