Corpus ID: 2865509

Generative Image Modeling Using Spatial LSTMs

@inproceedings{Theis2015GenerativeIM,
  title={Generative Image Modeling Using Spatial LSTMs},
  author={Lucas Theis and Matthias Bethge},
  booktitle={NIPS},
  year={2015}
}
  • Lucas Theis, Matthias Bethge
  • Published in NIPS 2015
  • Computer Science, Mathematics
  • 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 multidimensional long short-term memory units which are particularly suited for image modeling due to their spatial… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Paper Mentions

    BLOG POST

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 152 CITATIONS

    Pixel Recurrent Neural Networks

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Hierarchical Autoregressive Image Models with Auxiliary Decoders

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Image Transformer

    Spatial PixelCNN: Generating Images from Patches

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Conditional Image Generation with PixelCNN Decoders

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Visual Language Modeling on CNN Image Representations

    VIEW 1 EXCERPT
    CITES METHODS

    Progressively Diffused Networks for Semantic Image Segmentation

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis

    • Chao Yang, Xin Lu, +3 authors Hao Li
    • Computer Science
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2015
    2020

    CITATION STATISTICS

    • 14 Highly Influenced Citations

    • Averaged 25 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 61 REFERENCES

    Fields of Experts

    VIEW 1 EXCERPT