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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Digital surface model generation using traditional multi-view stereo matching(MVS) performs poorly over non-Lambertian surfaces, with asynchronousacquisitions, or at discontinuities. Neural radiance fields (NeRF) offer a newparadigm for reconstructing surface geometries using continuous volumetricrepresentation. NeRF is self-supervised, does not require ground truth geometryfor training, and provides an elegant way to include in its representationphysical parameters about the scene, thus potentially remedying the challengingscenarios where MVS fails. However, NeRF and its variants require many views toproduce convincing scene's geometries which in earth observation satelliteimaging is rare. In this paper we present SparseSat-NeRF (SpS-NeRF) - anextension of Sat-NeRF adapted to sparse satellite views. SpS-NeRF employs densedepth supervision guided by crosscorrelation similarity metric provided bytraditional semi-global MVS matching. We demonstrate the effectiveness of ourapproach on stereo and tri-stereo Pleiades 1B/WorldView-3 images, and compareagainst NeRF and Sat-NeRF. The code is available athttps://github.com/LulinZhang/SpS-NeRF

SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images