Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910550508699648 |
|---|---|
| author | Jeon, Subin Cho, In Kim, Minsu Cho, Woong Oh Kim, Seon Joo |
| author_facet | Jeon, Subin Cho, In Kim, Minsu Cho, Woong Oh Kim, Seon Joo |
| contents | We propose a new framework for creating and easily manipulating 3D models of arbitrary objects using casually captured videos. Our core ingredient is a novel hierarchy deformation model, which captures motions of objects with a tree-structured bones. Our hierarchy system decomposes motions based on the granularity and reveals the correlations between parts without exploiting any prior structural knowledge. We further propose to regularize the bones to be positioned at the basis of motions, centers of parts, sufficiently covering related surfaces of the part. This is achieved by our bone occupancy function, which identifies whether a given 3D point is placed within the bone. Coupling the proposed components, our framework offers several clear advantages: (1) users can obtain animatable 3D models of the arbitrary objects in improved quality from their casual videos, (2) users can manipulate 3D models in an intuitive manner with minimal costs, and (3) users can interactively add or delete control points as necessary. The experimental results demonstrate the efficacy of our framework on diverse instances, in reconstruction quality, interpretability and easier manipulation. Our code is available at https://github.com/subin6/HSNB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00351 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos Jeon, Subin Cho, In Kim, Minsu Cho, Woong Oh Kim, Seon Joo Computer Vision and Pattern Recognition We propose a new framework for creating and easily manipulating 3D models of arbitrary objects using casually captured videos. Our core ingredient is a novel hierarchy deformation model, which captures motions of objects with a tree-structured bones. Our hierarchy system decomposes motions based on the granularity and reveals the correlations between parts without exploiting any prior structural knowledge. We further propose to regularize the bones to be positioned at the basis of motions, centers of parts, sufficiently covering related surfaces of the part. This is achieved by our bone occupancy function, which identifies whether a given 3D point is placed within the bone. Coupling the proposed components, our framework offers several clear advantages: (1) users can obtain animatable 3D models of the arbitrary objects in improved quality from their casual videos, (2) users can manipulate 3D models in an intuitive manner with minimal costs, and (3) users can interactively add or delete control points as necessary. The experimental results demonstrate the efficacy of our framework on diverse instances, in reconstruction quality, interpretability and easier manipulation. Our code is available at https://github.com/subin6/HSNB. |
| title | Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00351 |