Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929297196843008 |
|---|---|
| author | Das, Devikalyan Wewer, Christopher Yunus, Raza Ilg, Eddy Lenssen, Jan Eric |
| author_facet | Das, Devikalyan Wewer, Christopher Yunus, Raza Ilg, Eddy Lenssen, Jan Eric |
| contents | Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no solution that can provide consistent, high-quality novel views from camera positions that are significantly different from the training views. In this work, we introduce Neural Parametric Gaussians (NPGs) to take on this challenge by imposing a two-stage approach: first, we fit a low-rank neural deformation model, which then is used as regularization for non-rigid reconstruction in the second stage. The first stage learns the object's deformations such that it preserves consistency in novel views. The second stage obtains high reconstruction quality by optimizing 3D Gaussians that are driven by the coarse model. To this end, we introduce a local 3D Gaussian representation, where temporally shared Gaussians are anchored in and deformed by local oriented volumes. The resulting combined model can be rendered as radiance fields, resulting in high-quality photo-realistic reconstructions of the non-rigidly deforming objects. We demonstrate that NPGs achieve superior results compared to previous works, especially in challenging scenarios with few multi-view cues. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_01196 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction Das, Devikalyan Wewer, Christopher Yunus, Raza Ilg, Eddy Lenssen, Jan Eric Computer Vision and Pattern Recognition Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no solution that can provide consistent, high-quality novel views from camera positions that are significantly different from the training views. In this work, we introduce Neural Parametric Gaussians (NPGs) to take on this challenge by imposing a two-stage approach: first, we fit a low-rank neural deformation model, which then is used as regularization for non-rigid reconstruction in the second stage. The first stage learns the object's deformations such that it preserves consistency in novel views. The second stage obtains high reconstruction quality by optimizing 3D Gaussians that are driven by the coarse model. To this end, we introduce a local 3D Gaussian representation, where temporally shared Gaussians are anchored in and deformed by local oriented volumes. The resulting combined model can be rendered as radiance fields, resulting in high-quality photo-realistic reconstructions of the non-rigidly deforming objects. We demonstrate that NPGs achieve superior results compared to previous works, especially in challenging scenarios with few multi-view cues. |
| title | Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.01196 |