Global Transport for Fluid Reconstruction with Learned Self-Supervision
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910883879321600 |
|---|---|
| author | Franz, Aleksandra Solenthaler, Barbara Thuerey, Nils |
| author_facet | Franz, Aleksandra Solenthaler, Barbara Thuerey, Nils |
| contents | We propose a novel method to reconstruct volumetric flows from sparse views via a global transport formulation. Instead of obtaining the space-time function of the observations, we reconstruct its motion based on a single initial state. In addition we introduce a learned self-supervision that constrains observations from unseen angles. These visual constraints are coupled via the transport constraints and a differentiable rendering step to arrive at a robust end-to-end reconstruction algorithm. This makes the reconstruction of highly realistic flow motions possible, even from only a single input view. We show with a variety of synthetic and real flows that the proposed global reconstruction of the transport process yields an improved reconstruction of the fluid motion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2104_06031 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Global Transport for Fluid Reconstruction with Learned Self-Supervision Franz, Aleksandra Solenthaler, Barbara Thuerey, Nils Computer Vision and Pattern Recognition Fluid Dynamics We propose a novel method to reconstruct volumetric flows from sparse views via a global transport formulation. Instead of obtaining the space-time function of the observations, we reconstruct its motion based on a single initial state. In addition we introduce a learned self-supervision that constrains observations from unseen angles. These visual constraints are coupled via the transport constraints and a differentiable rendering step to arrive at a robust end-to-end reconstruction algorithm. This makes the reconstruction of highly realistic flow motions possible, even from only a single input view. We show with a variety of synthetic and real flows that the proposed global reconstruction of the transport process yields an improved reconstruction of the fluid motion. |
| title | Global Transport for Fluid Reconstruction with Learned Self-Supervision |
| topic | Computer Vision and Pattern Recognition Fluid Dynamics |
| url | https://arxiv.org/abs/2104.06031 |