HackerPapers

arXiv:1601.04589cs.CV

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

Chuan Li, Michael Wand

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.

arXiv comments
9 pages, 9 figures
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 4 identifiable commenters in 5 comments across 5 threads, from Mar 2016 to Sep 2016. Found in 3 HN submissions from Jan 2016 to Jan 2016. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. Show HN: Wave function collapse algorithm 1 comment

    • Great work! The fact that it captures "long-range order" seemingly perfectly is something not many have been able to do before! And the "collapse" visualization is great fun to watch. But is your algorithm really qualitatively all that different from previous search methods…

      fitzwatermellowView on HNParent context

  2. Technologists have produced a 3D-printed painting in the style of Rembrandt 1 comment

    • Take a look at these: * Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis (http://arxiv.org/abs/1601.04589) * A Neural Algorithm of Artistic Style (http://arxiv.org/abs/1508.06576) They do much more than photoshopping. It's actual synthesis of…

      visargaView on HNParent context

  3. [dead] 1 comment

    • According to their about page, that site is using this algorithm http://arxiv.org/pdf/1508.06576.pdf whereas neural-image-analogies is a combination of http://www.mrl.nyu.edu/projects/image-analogies/index.html and http://arxiv.org/pdf/1601.04589v1.pdf Basically you can do a few…

      awentzonlineView on HNParent context

  4. Image Analogies using Neural Networks 1 comment
  5. Pictures combined using Neural networks 1 comment

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.