Corpus ID: 53715186

Learning to Generate the "Unseen" via Part Synthesis and Composition

@article{Schor2018LearningTG,
  title={Learning to Generate the "Unseen" via Part Synthesis and Composition},
  author={Nadav Schor and Oren Katzir and Hao Zhang and Daniel Cohen-Or},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.07441}
}
  • Nadav Schor, Oren Katzir, +1 author Daniel Cohen-Or
  • Published in ArXiv 2018
  • Computer Science
  • Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. [...] Key Method Treating a shape not as an unstructured whole, but as a (re-)composable set of deformable parts, adds a combinatorial dimension to the generative process to enrich the diversity of the output, encouraging the generator to venture more into the "unseen". We show that our part-based model generates richer variety of feasible shapes compared with a baseline generative model. To this end…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    7
    Twitter Mentions

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES

    Spatial Transformer Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Auto-Encoding Variational Bayes

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Generative Adversarial Nets

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Generative Image Inpainting with Contextual Attention

    VIEW 1 EXCERPT

    Global-to-local generative model for 3D shapes

    VIEW 2 EXCERPTS