L2 Divergence for Robust Colour Transfer

31st May 2019
L2 Divergence for Robust Colour Transfer

Optimal Transport is a very popular framework for performing colour transfer in images and videos. We have proposed an alternative framework where the cost function used for inferring a parametric transfer function is defined as the robust L2 divergence between two probability density functions. In this paper, we show that our approach combines many advantages of state of the art techniques and outperforms many recent algorithms as measured quantitatively with standard quality metrics, and qualitatively using perceptual studies. Mathematically, our formulation is presented in contrast to the Optimal Transport cost function that shares similarities with our cost function. Our formulation, however, is more flexible as it allows colour correspondences that may be available to be taken into account and performs well despite potential occurrences of correspondence outlier pairs. Our algorithm is shown to be fast, robust and it easily allows for user interaction providing freedom for artists to fine tune the recoloured images and videos.

Online Demo

DEMO: L2 Divergence for robust colour transfer

Code

Our code is available on Github!

Paper

L2 Divergence for robust colour transfer

Collaborators

Mairéad Grogan, Rozenn Dahyot.

Reference

Mairéad Grogan, Rozenn Dahyot.
L2 Divergence for robust colour transfer.
Computer Vision and Image Understanding, Volume 181, April 2019, Pages 39-49

Related Publication

User Interaction for Image Recolouring using L2

See Also

Our webpage describing all of our work in image recolouring using L2.