Corpus ID: 218502682

Neural Subdivision

@article{Liu2020NeuralS,
  title={Neural Subdivision},
  author={Hsueh-Ti Derek Liu and Vladimir G. Kim and Siddhartha Chaudhuri and Noam Aigerman and Alec Jacobson},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.01819}
}
  • Hsueh-Ti Derek Liu, Vladimir G. Kim, +2 authors Alec Jacobson
  • Published 2020
  • Computer Science
  • ArXiv
  • This paper introduces Neural Subdivision, a novel framework for data-driven coarse-to-fine geometry modeling. During inference, our method takes a coarse triangle mesh as input and recursively subdivides it to a finer geometry by applying the fixed topological updates of Loop Subdivision, but predicting vertex positions using a neural network conditioned on the local geometry of a patch. This approach enables us to learn complex non-linear subdivision schemes, beyond simple linear averaging… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 88 REFERENCES

    MeshCNN: A Network with an Edge

    Inter-surface mapping

    VIEW 2 EXCERPTS

    Scan2Mesh: From Unstructured Range Scans to 3D Meshes

    Variational Autoencoders for Deforming 3D Mesh Models

    VIEW 2 EXCERPTS

    Gaussian-product subdivision surfaces

    Surface Networks