Communication Dans Un Congrès Année : 2025

Gaussian Splatting for Efficient Satellite Image Photogrammetry

Résumé

Recently, Gaussian splatting has emerged as a strong alternative to NeRF, demonstrating impressive 3D modeling capabilities while requiring only a fraction of the training and rendering time. In this paper, we show how the standard Gaussian splatting framework can be adapted for remote sensing, retaining its high efficiency. This enables us to achieve state-of-the-art performance in just a few minutes, compared to the day-long optimization required by the best-performing NeRF-based Earth observation methods. The proposed framework incorporates remote-sensing improvements from EO-NeRF, such as radiometric correction and shadow modeling, while introducing novel components, including sparsity, view consistency, and opacity regularizations.

Fichier principal
Vignette du fichier
2412.13047v2.pdf (9.97 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05055200 , version 1 (04-05-2025)

Licence

Identifiants

  • HAL Id : hal-05055200 , version 1

Citer

Luca Savant Aira, Gabriele Facciolo, Thibaud Ehret. Gaussian Splatting for Efficient Satellite Image Photogrammetry. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), Jun 2025, Nashville, TN, United States. ⟨hal-05055200⟩
466 Consultations
354 Téléchargements

Partager

  • More