Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling
This addresses 3D modeling for computer graphics and vision, offering incremental improvements in surface quality and computational efficiency.
The paper tackles the problem of representing 3D surfaces by coupling explicit (atlas-based) and implicit (function-based) representations with consistency losses, resulting in smoother surfaces, more accurate normals, and improved occupancy functions compared to single-representation methods.
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.