First published: 2015/06/10 (9 years ago) 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.
