Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling

TL;DR

This paper introduces a hybrid neural architecture combining explicit atlas-based and implicit scalar functions for 3D surface modeling, improving surface quality and reconstruction efficiency.

Contribution

The novel integration of explicit and implicit surface representations with consistency losses enhances 3D modeling accuracy and enables efficient, differentiable rendering.

Findings

Produces smoother surfaces with better normals

Achieves more accurate implicit occupancy functions

Enables efficient, image-based training

Abstract

We propose a novel neural architecture for representing 3D surfaces, which harnesses two complementary shape representations: (i) an explicit representation via an atlas, i.e., embeddings of 2D domains into 3D; (ii) an implicit-function representation, i.e., a scalar function over the 3D volume, with its levels denoting surfaces. We make these two representations synergistic by introducing novel consistency losses that ensure that the surface created from the atlas aligns with the level-set of the implicit function. Our hybrid architecture outputs results which are superior to the output of the two equivalent single-representation networks, yielding smoother explicit surfaces with more accurate normals, and a more accurate implicit occupancy function. Additionally, our surface reconstruction step can directly leverage the explicit atlas-based representation. This process is computationally efficient, and can be directly used by differentiable rasterizers, enabling training our hybrid representation with image-based losses.