In this paper, we propose a new method, called guided synthesis, to synthesize a face cartoon from a face photo. The guided synthesis is defined as a local linear model, which generates a cartoon image by incorporating the content of guidance images taken from the training set. Our synthesis operation is achieved based on four weight functions. The first is a photo-photo weight that aims to measure the similarity between an input photo patch and a training photo patch. The second is defined as a photo-cartoon weight, which is used to compute the likelihood by computing the similarity between a cartoon patch and an input photo patch. The third weight is defined in the synthesized photos, which is to set a smoothness constraint between neighboring synthesized patches. The final weight is designed to evaluate the similarity of a synthesized patch to an input patch based on the spatial distance. Experimental evaluation on a number of face photos demonstrates the good performance of the proposed method on the face cartoon synthesis.
Hongliang Li, Guanghui Liu, and King Ngi Ngan, "Guided Face Cartoon Synthesis," IEEE Transactions on Multimedia, vol. 13, no. 6, pp. 1230-1239, 2011.
Examples of face photo-cartoon pairs. First row: Photos in CUHK face database. Second row: Corresponding cartoons drawn by an artist.
Face cartoon synthesis results. Columns 1 and 4: Face photos. Columns 2 and 5: Cartoon drawn by the artist; Columns 3 and 6: Synthesized cartoon.
The corresponding cropped results can be downloaded from
The original CUHK face images can be downloaded from MMlab in CUHK
2. Source Code (MATLAB)
Source code will be released as soon as possible
This work was partially supported by NSFC (No.60972109), the Program for New Century Excellent Talents in University (NCET-08-0090) and Sichuan Province Science Foundation for Youths (No. 2010JQ0003).