Improving NeRF with Height Data for Utilization of GIS Data
This work addresses the challenge of high computational cost in large-scale 3D scene reconstruction for applications in geographic information systems, representing an incremental improvement over existing NeRF methods.
The paper tackled the problem of applying Neural Radiance Fields (NeRF) to large-scale scenes by proposing a method that uses height data from GIS to divide scenes into objects and background with separate neural networks and adaptive sampling, resulting in improved image rendering accuracy and faster training speed.
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.