Communication Dans Un Congrès Année : 2025

Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints

Résumé

Shape-from-Template (SfT) refers to the class of methods that reconstruct the 3D shape of a deforming object from images/videos using a 3D template. Traditional SfT methods require point correspondences between images and the texture of the 3D template in order to reconstruct 3D shapes from images/videos in real time. Their performance severely degrades when encountered with severe occlusions in the images because of the unavailability of correspondences. In contrast, modern SfT methods use a correspondence-free approach by incorporating deep neural networks to reconstruct 3D objects, thus requiring huge amounts of data for supervision. Recent advances use a fully unsupervised or self-supervised approach by combining differentiable physics and graphics to deform 3D template to match input images. In this paper, we propose an unsupervised SfT which uses only image observations: color features, gradients and silhouettes along with a mesh inextensibility constraint to reconstruct at a 400× faster pace than (best-performing) unsupervised SfT. Moreover, when it comes to generating finer details and severe occlusions, our method outperforms the existing methodologies by a large margin. Code is available at https://github.com/dvttran/nsft.

Fichier principal
Vignette du fichier
2507.22699v1.pdf (13.1 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05199849 , version 1 (05-08-2025)

Licence

Identifiants

Citer

Thuy Tran, Ruochen Chen, Shaifali Parashar. Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints. International conference on computer vision, Oct 2025, Honolulu, United States. ⟨hal-05199849⟩
1080 Consultations
162 Téléchargements

Altmetric

Partager

  • More