Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.22699 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909008198107136 |
|---|---|
| author | Tran, Thuy Chen, Ruochen Parashar, Shaifali |
| author_facet | Tran, Thuy Chen, Ruochen Parashar, Shaifali |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints Tran, Thuy Chen, Ruochen Parashar, Shaifali Computer Vision and Pattern Recognition 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. |
| title | Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.22699 |