Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4952880 | Computers & Graphics | 2017 | 13 Pages |
â¢A texture-based framework for automatic color transfer and colorization.â¢An edge-aware texture descriptor based on multiscale gradient descent.â¢Stroke based edition for local color manipulation based on textures.
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.
Graphical abstractDownload high-res image (320KB)Download full-size image