Multi-View Inpainting for Image-Based Scene Editing and Rendering

Abstract : We propose a method to remove objects such as people and cars from multi-view urban image datasets, enabling free-viewpoint Image-Based Rendering (IBR) in the edited scenes. Our method combines information from multi-view 3D reconstruction with image inpainting techniques, by formulating the problem as an optimization of a global patch-based objective function. We use IBR techniques to reproject information from neighboring views, and 3D multi-view stereo reconstruction to perform multi-view coherent initialization for inpainting of pixels not filled by reprojection. Our algorithm performs multi-view consistent inpainting for color and 3D by blending reprojections with patch-based image inpaint-ing. We run our algorithm on casually captured datasets, and Google Street View data, removing objects such as cars, people and pillars, showing that our approach produces results of sufficient quality for free-viewpoint IBR on " cleaned up " scenes, as well as IBR scene editing, such as limited displacement of real objects.
Type de document :
Communication dans un congrès
2016 International Conference on 3D Vision (3DV), Oct 2016, Stanford, United States
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01369554
Contributeur : Theo Thonat <>
Soumis le : mercredi 21 septembre 2016 - 10:56:10
Dernière modification le : lundi 9 avril 2018 - 15:23:38
Document(s) archivé(s) le : jeudi 22 décembre 2016 - 12:47:47

Fichier

final_MVInpainting.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01369554, version 1

Collections

Citation

Theo Thonat, Eli Shechtman, Sylvain Paris, George Drettakis. Multi-View Inpainting for Image-Based Scene Editing and Rendering. 2016 International Conference on 3D Vision (3DV), Oct 2016, Stanford, United States. 〈hal-01369554〉

Partager

Métriques

Consultations de la notice

229

Téléchargements de fichiers

272