A Comparative Neural Radiance Field (NeRF) 3D Analysis of Camera Poses from HoloLens Trajectories and Structure from Motion
This work addresses 3D reconstruction for photogrammetry and augmented reality applications, presenting an incremental improvement by integrating HoloLens data with NeRFs.
The paper tackled 3D reconstruction by comparing camera poses from HoloLens trajectories and Structure from Motion for Neural Radiance Fields (NeRFs), finding that internal poses achieve a PSNR of 25 dB and refined poses reach 27 dB, with NeRFs outperforming conventional methods in completeness and detail.
Neural Radiance Fields (NeRFs) are trained using a set of camera poses and associated images as input to estimate density and color values for each position. The position-dependent density learning is of particular interest for photogrammetry, enabling 3D reconstruction by querying and filtering the NeRF coordinate system based on the object density. While traditional methods like Structure from Motion are commonly used for camera pose calculation in pre-processing for NeRFs, the HoloLens offers an interesting interface for extracting the required input data directly. We present a workflow for high-resolution 3D reconstructions almost directly from HoloLens data using NeRFs. Thereby, different investigations are considered: Internal camera poses from the HoloLens trajectory via a server application, and external camera poses from Structure from Motion, both with an enhanced variant applied through pose refinement. Results show that the internal camera poses lead to NeRF convergence with a PSNR of 25\,dB with a simple rotation around the x-axis and enable a 3D reconstruction. Pose refinement enables comparable quality compared to external camera poses, resulting in improved training process with a PSNR of 27\,dB and a better 3D reconstruction. Overall, NeRF reconstructions outperform the conventional photogrammetric dense reconstruction using Multi-View Stereo in terms of completeness and level of detail.