Corpus ID: 219530677

MeshSDF: Differentiable Iso-Surface Extraction

@article{Remelli2020MeshSDFDI,
  title={MeshSDF: Differentiable Iso-Surface Extraction},
  author={Edoardo Remelli and Artem Lukoianov and Stephan R. Richter and Benoit Guillard and Timur M. Bagautdinov and Pierr{\'e} Baqu{\'e} and Pascal Fua},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.03997}
}
  • Edoardo Remelli, Artem Lukoianov, +4 authors Pascal Fua
  • Published 2020
  • Computer Science
  • ArXiv
  • Geometric Deep Learning has recently made striking progress with the advent of continuous Deep Implicit Fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid, resulting in a learnable parameterization that is not limited in resolution. Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES

    A Papier-Mache Approach to Learning 3D Surface Generation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Marching Cubes: Learning Explicit Surface Representations

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning three-dimensional flow for interactive aerodynamic design

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Mesh R-CNN

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural 3D Mesh Renderer

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL