Transcoding a 3D Gaussian Splatting Model from a Plenoptic Point Cloud or Mesh without the Original Multi-view Images
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_ | 1866913148443820032 |
|---|---|
| author | Krivokuća, Maja Bendouro, Riad Sabater, Neus |
| author_facet | Krivokuća, Maja Bendouro, Riad Sabater, Neus |
| contents | In this paper, we propose an end-to-end transcoding pipeline, to create 3D Gaussian splatting (3DGS) models from existing 3D plenoptic point cloud or mesh models, when the original multi-view images of the captured 3D object or scene are not available. We also propose a custom initialisation to guide the 3DGS model learning, with constraints to ensure that the final 3DGS model aligns closely with the input point cloud or mesh surface. Tests on a high-quality, standard plenoptic point cloud dataset show that our pipeline produces 3DGS models of high visual quality, with many fewer splats than points in the original dense point clouds. Additionally, our custom initialisation leads to much faster convergence and cleaner surface representation than when starting from the default SfM-based initialisation that is typically used for 3DGS model learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21051 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transcoding a 3D Gaussian Splatting Model from a Plenoptic Point Cloud or Mesh without the Original Multi-view Images Krivokuća, Maja Bendouro, Riad Sabater, Neus Image and Video Processing In this paper, we propose an end-to-end transcoding pipeline, to create 3D Gaussian splatting (3DGS) models from existing 3D plenoptic point cloud or mesh models, when the original multi-view images of the captured 3D object or scene are not available. We also propose a custom initialisation to guide the 3DGS model learning, with constraints to ensure that the final 3DGS model aligns closely with the input point cloud or mesh surface. Tests on a high-quality, standard plenoptic point cloud dataset show that our pipeline produces 3DGS models of high visual quality, with many fewer splats than points in the original dense point clouds. Additionally, our custom initialisation leads to much faster convergence and cleaner surface representation than when starting from the default SfM-based initialisation that is typically used for 3DGS model learning. |
| title | Transcoding a 3D Gaussian Splatting Model from a Plenoptic Point Cloud or Mesh without the Original Multi-view Images |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2605.21051 |