Emerging Images Synthesis from Photographs

Mao-Fong Jian
National Tsing Hua University
Hung-Kuo Chu
National Tsing Hua University
Ruen-Rone Lee
National Tsing Hua University
Chia-Lun Ku
National Chiao Tung University
Yu-Shuen Wang
National Chiao Tung University
Chih-Yuan Yao
National Taiwan University of Science and Technology


In this work, we propose an automatic algorithm to synthesize emerging images from regular photographs. To generate images that are easy for human, rendered complex splats that capture silhouette and shading information of 3D objects.However, we realize that comparative information could be retrieved from photographs as well and replace the rendering of black complex splats with superpixels. They further take two post processing steps to make segmentation harder for bots, and both of them could find counterpart operations in image domain. Supporting by public image databases such as flickr and Picasa, we can envision a potential CAPTCHA application of our approach to massively and efficiently generate emerging images from photographs.



author = {Jian, Mao-Fong and Chu, Hung-Kuo and Lee, Ruen-Rone and Ku, Chia-Lun and Wang, Yu-Shuen and Yao, Chih-Yuan},
title = {Emerging Images Synthesis from Photographs},
booktitle = {ACM SIGGRAPH 2013 Posters},
series = {SIGGRAPH '13},
year = {2013},
pages = {97:1--97:1},
publisher = {ACM},