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. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.cag.2016.12.005 | Computers & Graphics |
Keywords | Field | DocType |
Texture analysis,Color transfer,Colorization,Stroke-based edition | Computer vision,Texture Descriptor,Color space,Color histogram,Local color,Computer science,Color balance,Artificial intelligence,Color quantization,Grayscale,Color image | Journal |
Volume | ISSN | Citations |
62 | 0097-8493 | 6 |
PageRank | References | Authors |
0.61 | 28 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
B. Arbelot | 1 | 6 | 0.95 |
Romain Vergne | 2 | 99 | 9.68 |
Thomas Hurtut | 3 | 129 | 12.02 |
Joëlle Thollot | 4 | 745 | 37.34 |