Existing 3D surface representation approaches are unable to accurately classify pixels and their orientation lying on the boundary of an object. Thus resulting in coarse representations which usually require post-processing steps to extract 3D surface meshes. To overcome this limitation, we propose an end-to-end trainable model that directly predicts implicit surface representations of arbitrary topology by optimising a novel geometric loss function. Specifically, we propose to represent the output as an oriented level set of a continuous embedding function, and incorporate this in a deep end-to-end learning framework by introducing a variational shape inference formulation. We investigate the benefits of our approach on the task of 3D surface prediction and demonstrate its ability to produce a more accurate reconstruction compared to voxel-based representations. We further show that our model is flexible and can be applied to a variety of shape inference problems.
@article{arxiv.1901.06802,
title = {Deep Level Sets: Implicit Surface Representations for 3D Shape Inference},
author = {Mateusz Michalkiewicz and Jhony K. Pontes and Dominic Jack and Mahsa Baktashmotlagh and Anders Eriksson},
journal= {arXiv preprint arXiv:1901.06802},
year = {2019}
}