Omni-nerf: neural radiance field from 360° image captures - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Omni-nerf: neural radiance field from 360° image captures

Résumé

This paper tackles the problem of novel view synthesis (NVS) from 360° images with imperfect camera poses or intrinsic parameters. We propose a novel end-to-end framework for training Neural Radiance Field (NeRF) models given only 360° RGB images and their rough poses, which we refer to as Omni-NeRF. We extend the pinhole camera model of NeRF to a more general camera model that better fits omni-directional fish-eye lenses. The approach jointly learns the scene geometry and optimizes the camera parameters without knowing the fisheye projection.
Fichier principal
Vignette du fichier
Omni_NeRF__Neural_Radiance_Field_from_360__image_captures_camera_ready.pdf (6.61 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03646688 , version 1 (19-04-2022)

Identifiants

  • HAL Id : hal-03646688 , version 1

Citer

Kai Gu, Thomas Maugey, Sebastian Knorr, Christine Guillemot. Omni-nerf: neural radiance field from 360° image captures. ICME 2022 - IEEE international conference on multimedia and expo, Jul 2022, Taipei, Taiwan. pp.1-6. ⟨hal-03646688⟩
545 Consultations
1631 Téléchargements

Partager

Gmail Facebook X LinkedIn More