Combining HoloLens with Instant-NeRFs: Advanced Real-Time 3D Mobile Mapping
This addresses the problem of fast and accurate 3D mapping for mobile applications, representing an incremental improvement by integrating existing technologies in a novel setup.
This paper tackles real-time 3D reconstruction by combining a Microsoft HoloLens 2 with a Neural Radiance Field (NeRF) to train a neural scene representation from RGB images and SLAM data, achieving extraction of five million scene points within 1 second using a specialized inference algorithm.
This work represents a large step into modern ways of fast 3D reconstruction based on RGB camera images. Utilizing a Microsoft HoloLens 2 as a multisensor platform that includes an RGB camera and an inertial measurement unit for SLAM-based camera-pose determination, we train a Neural Radiance Field (NeRF) as a neural scene representation in real-time with the acquired data from the HoloLens. The HoloLens is connected via Wifi to a high-performance PC that is responsible for the training and 3D reconstruction. After the data stream ends, the training is stopped and the 3D reconstruction is initiated, which extracts a point cloud of the scene. With our specialized inference algorithm, five million scene points can be extracted within 1 second. In addition, the point cloud also includes radiometry per point. Our method of 3D reconstruction outperforms grid point sampling with NeRFs by multiple orders of magnitude and can be regarded as a complete real-time 3D reconstruction method in a mobile mapping setup.