English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Generative Image Modeling Using Spatial LSTMs

MPS-Authors
/persons/resource/persons84256

Theis,  L
Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83805

Bethge,  M
Max Planck Institute for Biological Cybernetics, Max Planck Society;
Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator

Link
(Any fulltext)

Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Theis, L., & Bethge, M. (2016). Generative Image Modeling Using Spatial LSTMs. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, R. Garnett, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 28 (pp. 1918-1926). Red Hook, NY, USA: Curran.


Cite as: http://hdl.handle.net/21.11116/0000-0000-7AB2-E
Abstract
Modeling the distribution of natural images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks have been successful in capturing long-range dependencies in a number of problems but only recently have found their way into generative image models. We here introduce a recurrent image model based on multi-dimensional long short-term memory units which are particularly suited for image modeling due to their spatial structure. Our model scales to images of arbitrary size and its likelihood is computationally tractable. We find that it outperforms the state of the art in quantitative comparisons on several image datasets and produces promising results when used for texture synthesis and inpainting.