Gaussian Splatting Lucas-Kanade
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_ | 1866916663735091200 |
|---|---|
| author | Xie, Liuyue Julin, Joel Niinuma, Koichiro Jeni, Laszlo A. |
| author_facet | Xie, Liuyue Julin, Joel Niinuma, Koichiro Jeni, Laszlo A. |
| contents | Gaussian Splatting and its dynamic extensions are effective for reconstructing 3D scenes from 2D images when there is significant camera movement to facilitate motion parallax and when scene objects remain relatively static. However, in many real-world scenarios, these conditions are not met. As a consequence, data-driven semantic and geometric priors have been favored as regularizers, despite their bias toward training data and their neglect of broader movement dynamics.
Departing from this practice, we propose a novel analytical approach that adapts the classical Lucas-Kanade method to dynamic Gaussian splatting. By leveraging the intrinsic properties of the forward warp field network, we derive an analytical velocity field that, through time integration, facilitates accurate scene flow computation. This enables the precise enforcement of motion constraints on warp fields, thus constraining both 2D motion and 3D positions of the Gaussians. Our method excels in reconstructing highly dynamic scenes with minimal camera movement, as demonstrated through experiments on both synthetic and real-world scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11309 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Gaussian Splatting Lucas-Kanade Xie, Liuyue Julin, Joel Niinuma, Koichiro Jeni, Laszlo A. Computer Vision and Pattern Recognition Graphics Gaussian Splatting and its dynamic extensions are effective for reconstructing 3D scenes from 2D images when there is significant camera movement to facilitate motion parallax and when scene objects remain relatively static. However, in many real-world scenarios, these conditions are not met. As a consequence, data-driven semantic and geometric priors have been favored as regularizers, despite their bias toward training data and their neglect of broader movement dynamics. Departing from this practice, we propose a novel analytical approach that adapts the classical Lucas-Kanade method to dynamic Gaussian splatting. By leveraging the intrinsic properties of the forward warp field network, we derive an analytical velocity field that, through time integration, facilitates accurate scene flow computation. This enables the precise enforcement of motion constraints on warp fields, thus constraining both 2D motion and 3D positions of the Gaussians. Our method excels in reconstructing highly dynamic scenes with minimal camera movement, as demonstrated through experiments on both synthetic and real-world scenes. |
| title | Gaussian Splatting Lucas-Kanade |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2407.11309 |