Corpus ID: 214611877

Neural Contours: Learning to Draw Lines from 3D Shapes

@article{Liu2020NeuralCL,
  title={Neural Contours: Learning to Draw Lines from 3D Shapes},
  author={Difan Liu and Mohamed Nabail and Aaron Hertzmann and Evangelos Kalogerakis},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.10333}
}
  • Difan Liu, Mohamed Nabail, +1 author Evangelos Kalogerakis
  • Published 2020
  • Computer Science
  • ArXiv
  • This paper introduces a method for learning to generate line drawings from 3D models. Our architecture incorporates a differentiable module operating on geometric features of the 3D model, and an image-based module operating on view-based shape representations. At test time, geometric and view-based reasoning are combined with the help of a neural module to create a line drawing. The model is trained on a large number of crowdsourced comparisons of line drawings. Experiments demonstrate that… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 56 REFERENCES

    Line drawings from 3D models: A tutorial

    • Pierre Bénard, Aaron Hertzmann
    • Foundations and Trends in Computer Grapics and Vision,
    • 2019
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Where do people draw lines?

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Apparent ridges for line drawing

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Suggestive contours for conveying shape

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Why Do Line Drawings Work? A Realism Hypothesis

    Im2Pencil: Controllable Pencil Illustration From Photographs

    VIEW 2 EXCERPTS

    Line drawings from 3D models: A tutorial. Foundations and Trends in Computer Grapics and Vision

    • Pierre Bénard, Aaron Hertzmann
    • 2019