Proceedings/Recueil Des Communications Année : 2023

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

Résumé

Digital surface model generation using traditional multi-view stereo matching (MVS) performs poorly over non-Lambertian surfaces , with asynchronous acquisitions, or at discontinuities. Neural radiance fields (NeRF) offer a new paradigm for reconstructing surface geometries using continuous volumetric representation. NeRF is self-supervised, does not require ground truth geometry for training, and provides an elegant way to include in its representation physical parameters about the scene, thus potentially remedying the challenging scenarios where MVS fails. However, NeRF and its variants require many views to produce convincing scene's geometries which in earth observation satellite imaging is rare. In this paper we present SparseSat-NeRF (SpS-NeRF)-an extension of Sat-NeRF adapted to sparse satellite views. SpS-NeRF employs dense depth supervision guided by cross-correlation similarity metric provided by traditional semi-global MVS matching. We demonstrate the effectiveness of our approach on stereo and tri-stereo Pléiades 1B/WorldView-3 images, and compare against NeRF and Sat-NeRF. The code is available at https://github.com/LulinZhang/SpS-NeRF

Fichier principal
Vignette du fichier
SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images.pdf (4.31 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04205387 , version 1 (12-09-2023)

Licence

Identifiants

  • HAL Id : hal-04205387 , version 1

Citer

Lulin Zhang, Ewelina Rupnik. SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images. ISPRS Annals 2023, 2023. ⟨hal-04205387⟩
135 Consultations
156 Téléchargements

Partager

  • More