Texture-Generic Deep Shape-From-Template - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Access Année : 2021

Texture-Generic Deep Shape-From-Template

Résumé

Shape-from-Template (SfT) solves the registration and 3D reconstruction of a deformable 3D object, represented by the template, from a single image. Recently, methods based on deep learning have been able to solve SfT for the wide-baseline case in real-time, clearly surpassing classical methods. However, the main limitation of current methods is the need for fine tuning of the neural models to a specific geometry and appearance represented by the template texture map. We propose the first texture-generic deep learning SfT method which adapts to new texture maps at run-time, without the need for texture specific fine tuning. We achieve this by dividing the problem into a segmentation step and a registration and reconstruction step, both solved with deep learning. We include the template texture map as one of the neural inputs in both steps, training our models to adapt to different ones. We show that our method obtains comparable or better results to previous deep learning models, which are texture specific. It works in challenging imaging conditions, including complex deformations, occlusions, motion blur and poor textures. Our implementation runs in real-time, with a low-cost GPU and CPU.
Fichier principal
Vignette du fichier
Bartoli ACCESS Texture... EDITEUR OA.pdf (1.98 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03703678 , version 1 (24-06-2022)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

David Fuentes-Jimenez, Daniel Pizarro, David Casillas-Perez, Toby Collins, Adrien Bartoli. Texture-Generic Deep Shape-From-Template. IEEE Access, 2021, 9, pp.75211-75230. ⟨10.1109/ACCESS.2021.3082011⟩. ⟨hal-03703678⟩
10 Consultations
12 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More