Abstract : This paper targets two related color manipulation problems: Color transfer for modifying an image's colors and colorization for adding colors to a grayscale image. Automatic methods for these two applications propose to modify the input image using a reference that contains the desired colors. Previous approaches usually do not target both applications and suffer from two main limitations: possible misleading associations between input and reference regions and poor spatial coherence around image structures. In this paper, we propose a unified framework that uses the textural content of the images to guide the color transfer and colorization. Our method introduces an edge-aware texture descriptor based on region covariance, allowing for local color transformations. We show that our approach is able to produce results comparable or better than state-of-the-art methods in both applications.
https://hal.archives-ouvertes.fr/hal-01305596 Contributor : Benoit ArbelotConnect in order to contact the contributor Submitted on : Thursday, April 21, 2016 - 2:27:27 PM Last modification on : Tuesday, February 8, 2022 - 9:10:02 AM Long-term archiving on: : Friday, July 22, 2016 - 12:21:54 PM
Benoit Arbelot, Romain Vergne, Thomas Hurtut, Joëlle Thollot. Automatic Texture Guided Color Transfer and Colorization. Expressive 2016, May 2016, Lisbonne, Portugal. pp.21-32, ⟨10.2312/exp.20161060⟩. ⟨hal-01305596⟩