Painterly Image Generation

paint.01 + paint.03 = paint.02

We present a new technique for artistic style transferring by considering the perceptual structure matching between the source image and the target images. Given a photograph, our technique first searches for an existing art work on a similar scene through using the computational model of GIST perception and then transfers both the color and brush texture from it by considering the structure matching between the two images. The proposed method is fully automatic and can be used for transferring any styles.

Publications

  1. Masahiro Toyoura, Noriyuki Abe, Xiaoyang Mao, “Painterly Image Generation Using Scene-Aware Style Transferring,” Cyberworlds, 2016-9.
  2. Noriyuki Abe, Masahiro Toyoura, Xiaoyang Mao, “Style Transferring Using GIST,” International Symposium on Non-photorealistic Animation and Rendering (NPAR), Poster (Honorable Mention Award, Invited to SIGGRAPH Poster Session), 2011-8.