Consistent image analogies using semi-supervised learning

In this paper we study the following problem: given two source images A and A , and a target image B, can we learn to synthesize a new image B which relates to B in the same way that A relates to A? We propose an algorithm which a) uses a semi-supervised component to exploit the fact that the target image B is available apriori, b) uses inference on a Markov Random Field (MRF) to ensure global consistency, and c) uses image quilting to ensure local consistency. Our algorithm can also deal with the case when A is only partially labeled, that is, only small parts of A are available for training. Empirical evaluation shows that our algorithm consistently produces visually pleasing results, outperforming the state of the art.

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Li Cheng, S. V. N. Vishwanathan, Xinhua Zhang
• Keywords: Computer Vision, CVPR 2008, Global Consistency, Markov Random Field, Target Image B, Uses Image, Uses Inference