Deep Level Sets: Implicit Surface Representations for 3D Shape Inference

TL;DR

This paper introduces a novel deep learning method for 3D shape inference that directly predicts implicit surface representations using oriented level sets, resulting in more accurate 3D reconstructions without post-processing.

Contribution

It presents an end-to-end trainable model that employs a geometric loss and variational shape inference to improve 3D surface prediction accuracy over traditional voxel-based methods.

Findings

More accurate 3D surface reconstructions compared to voxel methods

Flexible application to various shape inference problems

Effective implicit surface representation with oriented level sets

Abstract

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.