Multi-Date Earth Observation NeRF: The Detail Is in the Shadows - HAL Accéder directement au contenu
Communication dans un congrès Année : 2023

Multi-Date Earth Observation NeRF: The Detail Is in the Shadows

Résumé

We introduce Earth Observation NeRF (EO-NeRF), a new method for digital surface modeling and novel view synthesis from collections of multi-date remote sensing images. In contrast to previous variants of NeRF proposed in the literature for satellite images, EO-NeRF outperforms the altitude accuracy of advanced pipelines for 3D reconstruction from multiple satellite images, including classic and learned stereovision methods. This is largely due to a rendering of building shadows that is strictly consistent with the scene geometry and independent from other transient phenomena. In addition to that, a number of strategies are also proposed with the aim to exploit raw satellite images. We add model parameters to circumvent usual pre-processing steps, such as the relative radiometric normalization of the input images and the bundle adjustment for refining the camera models. We evaluate our method on different areas of interest using sets of 10-20 pre-processed and raw pansharpened WorldView-3 images.
Fichier principal
Vignette du fichier
EO_NeRF__The_detail_is_in_the_shadows.pdf ( 36.53 Mo ) Télécharger
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-04290925, version 1 (21-11-2023)

Identifiants

Citer

Roger Marí, Gabriele Facciolo, Thibaud Ehret. Multi-Date Earth Observation NeRF: The Detail Is in the Shadows. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun 2023, Vancouver, Canada. pp.2035-2045, ⟨10.1109/CVPRW59228.2023.00197⟩. ⟨hal-04290925⟩
14 Consultations
1 Téléchargements
Dernière date de mise à jour le 26/06/2024
comment ces indicateurs sont-ils produits

Altmetric

Partager

Gmail Facebook Twitter LinkedIn Plus