Deep Meta Functionals for Shape Representation

Gidi Littwin, Lior Wolf; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 1824-1833

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Littwin_2019_ICCV,
author = {Littwin, Gidi and Wolf, Lior},
title = {Deep Meta Functionals for Shape Representation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}