Learning Generalizable Light Field Networks from Few Images - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2023

Learning Generalizable Light Field Networks from Few Images

Résumé

We explore a new strategy for few-shot novel view synthesis based on a neural light field representation. Given a target camera pose, an implicit neural network maps each ray to its target pixel’s color directly. The network is conditioned on local ray features generated by coarse volumetric rendering from an explicit 3D feature volume. This volume is built from the input images using a 3D ConvNet. Our method achieves competitive performances on real MVS data with respect to state-of-the-art neural radiance field based competition, while offering a roughly 50 times faster rendering.
Fichier principal
Vignette du fichier
Learning_Generalizable_Light_Field_Networks_from_Few_Images.pdf (3.83 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04116795 , version 1 (05-06-2023)

Licence

Identifiants

Citer

Qian Li, Franck Multon, Adnane Boukhayma. Learning Generalizable Light Field Networks from Few Images. ICASSP 2023 - IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, Jun 2023, Rhodes, Greece. pp.1-5, ⟨10.1109/icassp49357.2023.10096979⟩. ⟨hal-04116795⟩
73 Consultations
105 Téléchargements

Altmetric

Partager

More