Improving NeRF with Height Data for Utilization of GIS Data

TL;DR

This paper enhances Neural Radiance Fields (NeRF) for large-scale scene reconstruction by integrating height data from GIS, dividing scenes into objects and background, and employing adaptive sampling, resulting in improved accuracy and faster training.

Contribution

It introduces a novel method that utilizes height data to effectively segment large scenes and employs adaptive sampling to enhance NeRF performance.

Findings

Improved image rendering accuracy.

Faster training speed.

Effective large-scale scene reconstruction.

Abstract

Neural Radiance Fields (NeRF) has been applied to various tasks related to representations of 3D scenes. Most studies based on NeRF have focused on a small object, while a few studies have tried to reconstruct large-scale scenes although these methods tend to require large computational cost. For the application of NeRF to large-scale scenes, a method based on NeRF is proposed in this paper to effectively use height data which can be obtained from GIS (Geographic Information System). For this purpose, the scene space was divided into multiple objects and a background using the height data to represent them with separate neural networks. In addition, an adaptive sampling method is also proposed by using the height data. As a result, the accuracy of image rendering was improved with faster training speed.