Structure-Aware Nonlocal Optimization Framework for Image Colorization  

作　　者：赵汉理 聂桂芝 厉旭杰 金小刚 潘志庚 

机构地区：[1]Intelligent Information Systems Institute, Wenzhou University, Wenzhou 325035, China [2]State Key Lab of CAD & CG, Zhejiang University, Hangzhou 310058, China [3]Digital Media and HCI Research Center, Hangzhou Normal University, Hangzhou 311121, China

出　　处：《Journal of Computer Science & Technology》2015年第3期478-488,共11页计算机科学技术学报（英文版）

基　　金：This work was supported by the National Natural Science Foundation of China under Grant Nos. 61100146 and 61472351, and the Zhejiang Provincial Natural Science Foundation of China under Grant Nos. LY15F020019 and LQ14F020006. Pan was supported by the National Key Technology Research and Development Program of the Ministry of Science and Technology of China under Grant No. 2013BAH24F01. Acknowledgement CVM 2015 anonymous We would like to thank our reviewers for their constructive and helpful comments which definitely improve ttle quality of the paper.

摘　　要：This paper proposes a structure-aware nonlocal energy optimization framework for interactive image colo- rization with sparse scribbles. Our colorization technique propagates colors to both local intensity-continuous regions and remote texture-similar regions without explicit image segmentation. We implement the nonlocal principle by computing k nearest neighbors in the high-dimensional feature space. The feature space contains not only image coordinates and intensities but also statistical texture features obtained with the direction-aligned Gabor wavelet filter. Structure maps are utilized to scale texture features to avoid artifacts along high-contrast boundaries. We show various experimental results and comparisons on image colorization, selective recoloring and decoloring, and progressive color editing to demonstrate the effectiveness of the proposed approach.This paper proposes a structure-aware nonlocal energy optimization framework for interactive image colo- rization with sparse scribbles. Our colorization technique propagates colors to both local intensity-continuous regions and remote texture-similar regions without explicit image segmentation. We implement the nonlocal principle by computing k nearest neighbors in the high-dimensional feature space. The feature space contains not only image coordinates and intensities but also statistical texture features obtained with the direction-aligned Gabor wavelet filter. Structure maps are utilized to scale texture features to avoid artifacts along high-contrast boundaries. We show various experimental results and comparisons on image colorization, selective recoloring and decoloring, and progressive color editing to demonstrate the effectiveness of the proposed approach.

关 键 词：COLORIZATION recoloring feature space relative total variation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP273[自动化与计算机技术—计算机科学与技术]