{"ID":2888816,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22699","arxiv_id":"2507.22699","title":"Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints","abstract":"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 $400\\times$ 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.","short_abstract":"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....","url_abs":"https://arxiv.org/abs/2507.22699","url_pdf":"https://arxiv.org/pdf/2507.22699v1","authors":"[\"Thuy Tran\",\"Ruochen Chen\",\"Shaifali Parashar\"]","published":"2025-07-30T14:09:39Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611582,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888816,"paper_url":"https://arxiv.org/abs/2507.22699","paper_title":"Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints","repo_url":"https://github.com/dvttran/nsft","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}