MeshSDF: Differentiable Iso-Surface Extraction

Edoardo Remelli, Artem Lukoianov, Stephan Richter, Benoit Guillard, Timur Bagautdinov, Pierre Baque, Pascal Fua

NeurIPS 2020

/neurips/2020/remelli2020neurips-meshsdf/

Abstract

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.

PDF NeurIPS Semantic Scholar

Cite

Text

Remelli et al. "MeshSDF: Differentiable Iso-Surface Extraction." Neural Information Processing Systems, 2020.

Markdown

[Remelli et al. "MeshSDF: Differentiable Iso-Surface Extraction." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/remelli2020neurips-meshsdf/)

BibTeX

@inproceedings{remelli2020neurips-meshsdf,
  title     = {{MeshSDF: Differentiable Iso-Surface Extraction}},
  author    = {Remelli, Edoardo and Lukoianov, Artem and Richter, Stephan and Guillard, Benoit and Bagautdinov, Timur and Baque, Pierre and Fua, Pascal},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/remelli2020neurips-meshsdf/}
}