The Community for Technology Leaders
Green Image
Issue No. 11 - Nov. (2012 vol. 18)
ISSN: 1077-2626
pp: 1849-1857
Jiaya Jia , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Hong Kong, China
Ming-Ming Cheng , TNList, Tsinghua Univ., Beijing, China
Fang-Lue Zhang , TNList, Tsinghua Univ., Beijing, China
Shi-Min Hu , TNList, Tsinghua Univ., Beijing, China
ABSTRACT
We present a semiautomatic image editing framework dedicated to individual structured object replacement from groups. The major technical difficulty is element separation with irregular spatial distribution, hampering previous texture, and image synthesis methods from easily producing visually compelling results. Our method uses the object-level operations and finds grouped elements based on appearance similarity and curvilinear features. This framework enables a number of image editing applications, including natural image mixing, structure preserving appearance transfer, and texture mixing.
INDEX TERMS
image texture, feature extraction, texture mixing, ImageAdmixture, dissimilar objects, semiautomatic image editing framework, structured object replacement, element separation, irregular spatial distribution, image synthesis methods, visually compelling results, object-level operations, appearance similarity, curvilinear features, natural image mixing, structure preserving appearance transfer, Shape, Visualization, Feature extraction, Vectors, Active contours, Image segmentation, Image color analysis, image processing, Natural image, structure analysis, texture
CITATION
Jiaya Jia, Ming-Ming Cheng, Fang-Lue Zhang, Shi-Min Hu, "ImageAdmixture: Putting Together Dissimilar Objects from Groups", IEEE Transactions on Visualization & Computer Graphics, vol. 18, no. , pp. 1849-1857, Nov. 2012, doi:10.1109/TVCG.2012.68
119 ms
(Ver )