ML Anthology

Deep Meta Functionals for Shape Representation

Gidi Littwin, Lior Wolf
ICCV 2019
doi:10.1109/ICCV.2019.00191 /iccv/2019/littwin2019iccv-deep/

Abstract

We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights. The network parametrized by these weights represents a 3D shape by classifying every point in the volume as either within or outside the shape. The new representation has virtually unlimited capacity and resolution, and can have an arbitrary topology. Our experiments show that it leads to more accurate shape inference from a 2D projection than the existing methods, including voxel-, silhouette-, and mesh-based methods. The code will be available at: https: //github.com/gidilittwin/Deep-Meta.

PDF ICCV Semantic Scholar

Cite

Text

Littwin and Wolf. "Deep Meta Functionals for Shape Representation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00191

Markdown

[Littwin and Wolf. "Deep Meta Functionals for Shape Representation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/littwin2019iccv-deep/) doi:10.1109/ICCV.2019.00191

BibTeX

@inproceedings{littwin2019iccv-deep,
  title     = {{Deep Meta Functionals for Shape Representation}},
  author    = {Littwin, Gidi and Wolf, Lior},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00191},
  url       = {https://mlanthology.org/iccv/2019/littwin2019iccv-deep/}
}