Color Transfer and Colorization based on Textural Properties
نویسندگان
چکیده
This paper targets two related color manipulation problems: Color transfer for modifying an image colors and colorization for adding colors to a greyscale 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 su er 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 uni ed 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. Key-words: Color transfer, colorization, textures ∗ Inria-LJK (UGA, CNRS) † Polytechnique Montréal Transfert de couleurs et colorisation basés sur des propriétés texturelles Résumé : Cet article se concentre sur deux problèmes de manipulation de couleurs liés : le transfert de couleurs qui modi e les couleurs d'une image, et la colorisation qui ajoute des couleurs à une image en niveaux de gris. Les méthodes automatiques pour ces deux applications modi ent l'image d'entrée à l'aide d'une image de référence contenant les couleurs désirées. Les approches précédentes visent rarement les deux problèmes simultanement et sou rent de deux principales limitations : les correspondances créées entre les images d'entrée et de référence sont incorrectes ou approximatives, et une mauvaise cohérence spatiale autour des structures de l'image. Dans cet article, nous proposons un pipeline uni ant les deux problèmes, basé sur le contenu texturel des images pour guider le transfert ou la colorisation. Notre méthode introduit un descripteur de textures préservant les contours de l'image, basé sur des matrices de covariance, permettant d'appliquer des transformations de couleurs locales. Nous montrons que notre approche est capable de produire des résultats comparables ou meilleurs que d'autres méthodes de l'état de l'art dans les deux applications. Mots-clés : Transfert de couleurs, colorisation, textures Color Transfer and Colorization based on Textural Properties 3
منابع مشابه
Texture-adaptive image colorization framework
In this paper we present how to exploit the textural information to improve scribble-based image colorization. Although many methods have been already proposed for coloring grayscale images based on a set of color scribbles inserted by a user, very few of them take into account textural properties. We demonstrate that the textural information can be extremely helpful for this purpose and it may...
متن کاملTextural features for scribble-based image colorization
In this paper we propose how to exploit image textural features to improve scribble-based image colorization. The existing techniques work by propagating color from the user-added scribbles over the whole image. The color propagation paths are determined so as to minimize the luminance changes integrated along the path. In our method, at first linear discriminant analysis is performed over the ...
متن کاملAutomatic Texture Guided Color Transfer and Colorization
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: poss...
متن کاملImage Colorization Using Discriminative Textural Features
This paper presents a novel approach to scribblebased image colorization. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we extract the most discriminative features using linear discriminant analysis (LDA). After that, the whole image is projected onto a discriminative textural feature space. Our main contrib...
متن کاملExample Based Colorization Using Optimization
In this paper, we present an example-based colorization method to colorize a gray image. Besides the gray target image, the user only needs to provide a reference color image which is semantically similar to the gray image. We first segment both the target image and reference image and find correspondences at the segmentation level between these two images. The use of segmentation level can not...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016