NerfBridge: Bringing Real-time, Online Neural Radiance Field Training to Robotics

TL;DR

NerfBridge enables real-time, online training of neural radiance fields (NeRFs) directly from robotic sensors, facilitating rapid development of NeRF-based applications in robotics by integrating ROS with Nerfstudio.

Contribution

This work introduces NerfBridge, an open-source interface that connects ROS with Nerfstudio, allowing real-time NeRF training from streaming images in robotic systems.

Findings

Enables NeRF training in real-time on robotic platforms.

Demonstrated NeRF training on a quadrotor in indoor and outdoor environments.

Provides an extensible framework for robotics research using NeRFs.

Abstract

This work was presented at the IEEE International Conference on Robotics and Automation 2023 Workshop on Unconventional Spatial Representations. Neural radiance fields (NeRFs) are a class of implicit scene representations that model 3D environments from color images. NeRFs are expressive, and can model the complex and multi-scale geometry of real world environments, which potentially makes them a powerful tool for robotics applications. Modern NeRF training libraries can generate a photo-realistic NeRF from a static data set in just a few seconds, but are designed for offline use and require a slow pose optimization pre-computation step. In this work we propose NerfBridge, an open-source bridge between the Robot Operating System (ROS) and the popular Nerfstudio library for real-time, online training of NeRFs from a stream of images. NerfBridge enables rapid development of research on applications of NeRFs in robotics by providing an extensible interface to the efficient training pipelines and model libraries provided by Nerfstudio. As an example use case we outline a hardware setup that can be used NerfBridge to train a NeRF from images captured by a camera mounted to a quadrotor in both indoor and outdoor environments. For accompanying video https://youtu.be/EH0SLn-RcDg and code https://github.com/javieryu/nerf_bridge.