Pré-Publication, Document De Travail Année : 2025

Fused-Planes: Improving Planar Representations for Learning Large Sets of 3D Scenes

Résumé

To learn large sets of scenes, Tri-Planes are commonly employed for their planar structure that enables an interoperability with image models, and thus diverse 3D applications. However, this advantage comes at the cost of resource efficiency, as Tri-Planes are not the most computationally efficient option. In this paper, we introduce Fused-Planes, a new planar architecture that improves Tri-Planes resource-efficiency in the framework of learning large sets of scenes, which we call "multi-scene inverse graphics". To learn a large set of scenes, our method divides it into two subsets and operates as follows: (i) we train the first subset of scenes jointly with a compression model, (ii) we use that compression model to learn the remaining scenes. This compression model consists of a 3D-aware latent space in which Fused-Planes are learned, enabling a reduced rendering resolution, and shared structures across scenes that reduce scene representation complexity. Fused-Planes present competitive resource costs in multi-scene inverse graphics, while preserving Tri-Planes rendering quality, and maintaining their widely favored planar structure. Our codebase is publicly available as open-source. Our project page can be found at https://fused-planes.github.io .
Fichier principal
Vignette du fichier
Fused_Planes___Improving_Planar_Representations_for_Learning_Large_Sets_of_3D_Scenes__arxiv_.pdf (2) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04761470 , version 1 (31-10-2024)
hal-04761470 , version 2 (31-01-2025)

Identifiants

  • HAL Id : hal-04761470 , version 2

Citer

Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, et al.. Fused-Planes: Improving Planar Representations for Learning Large Sets of 3D Scenes. 2025. ⟨hal-04761470v2⟩
95 Consultations
43 Téléchargements

Partager

More