The Community for Technology Leaders
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Las Vegas, NV, United States
June 27, 2016 to June 30, 2016
ISSN: 1063-6919
ISBN: 978-1-4673-8851-1
pp: 2479-2486
ABSTRACT
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level. We apply the method to both photographic and non-photo-realistic (artwork) synthesis tasks. The MRF regularizer prevents over-excitation artifacts and reduces implausible feature mixtures common to previous dCNN inversion approaches, permitting synthezing photographic content with increased visual plausibility. Unlike standard MRF-based texture synthesis, the combined system can both match and adapt local features with considerable variability, yielding results far out of reach of classic generative MRF methods.
INDEX TERMS
Layout, Image generation, Image coding, Neural networks, Encoding, Image reconstruction
CITATION

C. Li and M. Wand, "Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, United States, 2016, pp. 2479-2486.
doi:10.1109/CVPR.2016.272
167 ms
(Ver 3.3 (11022016))