User Interaction for Image Recolouring using L2

 

Recently, an example based colour transfer approach proposed modelling the colour distributions of a palette and target image using Gaussian Mixture Models, and registers them by minimising the robust L2 distance between the mixtures. In this work we propose to extend this approach to allow for user interaction. We present two interactive recolouring applications, the first allowing the user to select colour correspondences between a target and palette image, while the second palette based application allows the user to edit a palette of colours to determine the image recolouring. We modify the L2 based cost function to improve results when an interactive interface is used, and take measures to ensure that even when minimal input is given by the user, good colour transfer results are created. Both applications are available through a web interface and qualitatively assessed against recent recolouring techniques.

Try out our online demos at the following links:

DEMO: Correspondence-based User Interaction for Image Recolouring using L2

DEMO: Palette-based User Interaction for Image Recolouring using L2

The video below shows our interactive recolouring tools in action:

Video: User Interaction for Image Recolouring using L2

References

[1] User Interaction for Image Recolouring using L2 , Mairéad Grogan, Rozenn Dahyot and Aljosa Smolic, In Proceedings of Conference on Visual Media Production, London, UK, December 2017 (CVMP ’17).