Accurate Differential Operators for Hybrid Neural Fields

TL;DR

This paper introduces methods to improve the accuracy of spatial derivatives in hybrid neural fields, enhancing their performance in rendering, simulation, and PDE solving.

Contribution

It proposes a post hoc polynomial fitting technique and a self-supervised fine-tuning method to obtain more accurate derivatives from hybrid neural fields.

Findings

More accurate derivatives reduce artifacts in rendering.

Enhanced simulations and PDE solutions.

Improved downstream application performance.

Abstract

Neural fields have become widely used in various fields, from shape representation to neural rendering, and for solving partial differential equations (PDEs). With the advent of hybrid neural field representations like Instant NGP that leverage small MLPs and explicit representations, these models train quickly and can fit large scenes. Yet in many applications like rendering and simulation, hybrid neural fields can cause noticeable and unreasonable artifacts. This is because they do not yield accurate spatial derivatives needed for these downstream applications. In this work, we propose two ways to circumvent these challenges. Our first approach is a post hoc operator that uses local polynomial fitting to obtain more accurate derivatives from pre-trained hybrid neural fields. Additionally, we also propose a self-supervised fine-tuning approach that refines the hybrid neural field to yield accurate derivatives directly while preserving the initial signal. We show applications of our method to rendering, collision simulation, and solving PDEs. We observe that using our approach yields more accurate derivatives, reducing artifacts and leading to more accurate simulations in downstream applications.