PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911669388574720 |
|---|---|
| author | Lee, Jihyun Lee, Changmin Kim, Donghwan Kim, Tae-Kyun |
| author_facet | Lee, Jihyun Lee, Changmin Kim, Donghwan Kim, Tae-Kyun |
| contents | While existing methods for reconstructing hand-object interactions have made impressive progress, they either focus on rigid or part-wise rigid objects-limiting their ability to model real-world objects (e.g., cloth, stuffed animals) that exhibit highly non-rigid deformations-or model deformable objects without full 3D hand reconstruction. To bridge this gap, we present PhysHanDI (Physics-based Reconstruction of Hand and Deformable Object Interactions), a framework that enables full 3D reconstruction of both interacting hands and non-rigid objects. Our key idea is to physically simulate object deformations driven by forces induced from densely reconstructed 3D hand motions, ensuring that the reconstructed object dynamics are both physically plausible and coherent with the interacting hand movements. Furthermore, we demonstrate that such simulation of object deformations can, in turn, refine and improve hand reconstruction via inverse physics. In experiments, PhysHanDI outperforms the state-of-the-art baseline across reconstruction and future prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09538 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions Lee, Jihyun Lee, Changmin Kim, Donghwan Kim, Tae-Kyun Computer Vision and Pattern Recognition Artificial Intelligence Robotics While existing methods for reconstructing hand-object interactions have made impressive progress, they either focus on rigid or part-wise rigid objects-limiting their ability to model real-world objects (e.g., cloth, stuffed animals) that exhibit highly non-rigid deformations-or model deformable objects without full 3D hand reconstruction. To bridge this gap, we present PhysHanDI (Physics-based Reconstruction of Hand and Deformable Object Interactions), a framework that enables full 3D reconstruction of both interacting hands and non-rigid objects. Our key idea is to physically simulate object deformations driven by forces induced from densely reconstructed 3D hand motions, ensuring that the reconstructed object dynamics are both physically plausible and coherent with the interacting hand movements. Furthermore, we demonstrate that such simulation of object deformations can, in turn, refine and improve hand reconstruction via inverse physics. In experiments, PhysHanDI outperforms the state-of-the-art baseline across reconstruction and future prediction. |
| title | PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2605.09538 |