A General Implicit Framework for Fast NeRF Composition and Rendering

TL;DR

This paper introduces a versatile implicit framework for fast NeRF composition and rendering, enabling real-time object placement, dynamic shadows, and seamless integration across various NeRF methods using Neural Depth Fields and an intersection neural network.

Contribution

It presents a novel general pipeline for rapid NeRF object composition, introducing Neural Depth Fields and an intersection neural network for efficient spatial relationship computation.

Findings

Enables real-time NeRF object composition and rendering.

Supports dynamic shadows with analytical light sources.

Compatible with various NeRF methods for quick previewing.

Abstract

A variety of Neural Radiance Fields (NeRF) methods have recently achieved remarkable success in high render speed. However, current accelerating methods are specialized and incompatible with various implicit methods, preventing real-time composition over various types of NeRF works. Because NeRF relies on sampling along rays, it is possible to provide general guidance for acceleration. To that end, we propose a general implicit pipeline for composing NeRF objects quickly. Our method enables the casting of dynamic shadows within or between objects using analytical light sources while allowing multiple NeRF objects to be seamlessly placed and rendered together with any arbitrary rigid transformations. Mainly, our work introduces a new surface representation known as Neural Depth Fields (NeDF) that quickly determines the spatial relationship between objects by allowing direct intersection computation between rays and implicit surfaces. It leverages an intersection neural network to query NeRF for acceleration instead of depending on an explicit spatial structure.Our proposed method is the first to enable both the progressive and interactive composition of NeRF objects. Additionally, it also serves as a previewing plugin for a range of existing NeRF works.