English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Neural Radiance Fields (NeRFs) are trained using a set of camera poses andassociated images as input to estimate density and color values for eachposition. The position-dependent density learning is of particular interest forphotogrammetry, enabling 3D reconstruction by querying and filtering the NeRFcoordinate system based on the object density. While traditional methods likeStructure from Motion are commonly used for camera pose calculation inpre-processing for NeRFs, the HoloLens offers an interesting interface forextracting the required input data directly. We present a workflow forhigh-resolution 3D reconstructions almost directly from HoloLens data usingNeRFs. Thereby, different investigations are considered: Internal camera posesfrom the HoloLens trajectory via a server application, and external cameraposes from Structure from Motion, both with an enhanced variant applied throughpose refinement. Results show that the internal camera poses lead to NeRFconvergence with a PSNR of 25\,dB with a simple rotation around the x-axis andenable a 3D reconstruction. Pose refinement enables comparable quality comparedto external camera poses, resulting in improved training process with a PSNR of27\,dB and a better 3D reconstruction. Overall, NeRF reconstructions outperformthe conventional photogrammetric dense reconstruction using Multi-View Stereoin terms of completeness and level of detail.

A Comparative Neural Radiance Field (NeRF) 3D Analysis of Camera Poses from HoloLens Trajectories and Structure from Motion