RefinedFields: Radiance Fields Refinement for Unconstrained Scenes - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

RefinedFields: Radiance Fields Refinement for Unconstrained Scenes

Résumé

Modeling large scenes from unconstrained images has proven to be a major challenge in computer vision. Existing methods tackling in-the-wild scene modeling operate in closed-world settings, where no conditioning on priors acquired from real-world images is present. We propose RefinedFields, which is, to the best of our knowledge, the first method leveraging pre-trained models to improve in-the-wild scene modeling. We employ pre-trained networks to refine K-Planes representations via optimization guidance using an alternating training procedure. We carry out extensive experiments and verify the merit of our method on synthetic data and real tourism photo collections. RefinedFields enhances rendered scenes with richer details and improves upon its base representation on the task of novel view synthesis in the wild. Our project page can be found at https://refinedfields.github.io.
Fichier principal
Vignette du fichier
rf_v2.pdf (21.62 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04318414 , version 1 (01-12-2023)
hal-04318414 , version 2 (07-02-2024)
hal-04318414 , version 3 (19-04-2024)

Licence

Paternité

Identifiants

Citer

Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi, Laurent Caraffa, Jeremie Mary, et al.. RefinedFields: Radiance Fields Refinement for Unconstrained Scenes. 2023. ⟨hal-04318414v3⟩
80 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More