Authors: Ying Tang Xiaoying Shi Tingzhe Xiao Jing Fan
Publish Date: 2012/04/19
Volume: 28, Issue: 6-8, Pages: 743-753
Abstract
The image analogy framework is especially useful to synthesize appealing images for nonhomogeneous input and gives users creative control over the synthesized results However the traditional framework did not adaptively employ the searching strategy based on neighborhood’s different textural contents Besides the synthesis speed is slow due to intensive computation involved in neighborhood matching In this paper we present a CUDAbased neighborhood matching algorithm for image analogy Our algorithm adaptively applies the global search of the exact L 2 nearest neighbor and kcoherence search strategies during synthesis according to different textural features of images which is especially usefully for nonhomogeneous textures To consistently implement the above two search strategies on GPU we adopt the fast K Nearest Neighbor searching algorithm based on CUDA Such an acceleration greatly reduces the time of the preprocess of kcoherence search and the synthesis procedure of the global search which makes possible the adjustment of important synthesis parameters We further adopt synthesis magnification to get the final highresolution synthesis image for running efficiency Experimental results show that our algorithm is suitable for various applications of the image analogy framework and takes full advantage of GPU’s parallel processing capability to improve synthesis speed and get satisfactory synthesis resultsThis work is supported by National Natural Science Foundation of China 61173097 61003265 Zhejiang Natural Science Foundation of China Z1090459 Y1080669 Zhejiang Science and Technology Planning Project of China No 2010C 33046 and Tsinghua–Tencent Joint Laboratory for Internet Innovation Technology
Keywords: