Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2479 - 2486
• Main Authors: Chuan Li, Wand, Michael
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Encoding; Image coding; Image generation; Image reconstruction; Layout; Neural networks

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, controlling the image layout at an abstract level. W...