On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes

TL;DR

This paper demonstrates that weight-encoded neural implicit functions are a viable and effective 3D shape representation, offering improved accuracy, robustness, and scalability over latent-encoded methods, with applications in 3D reconstruction and compression.

Contribution

The paper establishes weight-encoded neural implicits as a first-class 3D shape representation and introduces techniques to enhance their reconstruction accuracy and robustness.

Findings

Outperforms standard geometry processing compression techniques.

Shows superior robustness and scalability compared to latent-encoded methods.

Achieves high reconstruction accuracy for signed distance fields.

Abstract

A neural implicit outputs a number indicating whether the given query point in space is inside, outside, or on a surface. Many prior works have focused on _latent-encoded_ neural implicits, where a latent vector encoding of a specific shape is also fed as input. While affording latent-space interpolation, this comes at the cost of reconstruction accuracy for any _single_ shape. Training a specific network for each 3D shape, a _weight-encoded_ neural implicit may forgo the latent vector and focus reconstruction accuracy on the details of a single shape. While previously considered as an intermediary representation for 3D scanning tasks or as a toy-problem leading up to latent-encoding tasks, weight-encoded neural implicits have not yet been taken seriously as a 3D shape representation. In this paper, we establish that weight-encoded neural implicits meet the criteria of a first-class 3D shape representation. We introduce a suite of technical contributions to improve reconstruction accuracy, convergence, and robustness when learning the signed distance field induced by a polygonal mesh -- the _de facto_ standard representation. Viewed as a lossy compression, our conversion outperforms standard techniques from geometry processing. Compared to previous latent- and weight-encoded neural implicits we demonstrate superior robustness, scalability, and performance.