# Deep Meta Functionals for Shape Representation

## TL;DR

This paper introduces a novel deep learning approach for 3D shape reconstruction from a single image, using a network that directly predicts shape-representing weights, resulting in high-resolution, topologically flexible 3D models.

## Contribution

It proposes a new shape representation method that allows for unlimited capacity and arbitrary topology, improving accuracy over existing voxel, silhouette, and mesh-based methods.

## Key findings

- More accurate shape inference from 2D images.
- Supports arbitrary topology and high resolution.
- Outperforms existing shape reconstruction methods.

## 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 \textcolor{black}{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 is available at: https://github.com/gidilittwin/Deep-Meta