Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.06400 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909775651930112 |
|---|---|
| author | Gendrin, Matthieu Pateux, Stéphane Ladune, Théo |
| author_facet | Gendrin, Matthieu Pateux, Stéphane Ladune, Théo |
| contents | 3D Gaussian Splatting (3DGS) is a major breakthrough in 3D scene reconstruction. With a number of views of a given object or scene, the algorithm trains a model composed of 3D gaussians, which enables the production of novel views from arbitrary points of view. This freedom of movement is referred to as 6DoF for 6 degrees of freedom: a view is produced for any position (3 degrees), orientation of camera (3 other degrees). On large scenes, though, the input views are acquired from a limited zone in space, and the reconstruction is valuable for novel views from the same zone, even if the scene itself is almost unlimited in size. We refer to this particular case as 3DoF+, meaning that the 3 degrees of freedom of camera position are limited to small offsets around the central position. Considering the problem of coordinate quantization, the impact of position error on the projection error in pixels is studied. It is shown that the projection error is proportional to the squared inverse distance of the point being projected. Consequently, a new quantization scheme based on spherical coordinates is proposed. Rate-distortion performance of the proposed method are illustrated on the well-known Garden scene. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06400 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom Gendrin, Matthieu Pateux, Stéphane Ladune, Théo Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) is a major breakthrough in 3D scene reconstruction. With a number of views of a given object or scene, the algorithm trains a model composed of 3D gaussians, which enables the production of novel views from arbitrary points of view. This freedom of movement is referred to as 6DoF for 6 degrees of freedom: a view is produced for any position (3 degrees), orientation of camera (3 other degrees). On large scenes, though, the input views are acquired from a limited zone in space, and the reconstruction is valuable for novel views from the same zone, even if the scene itself is almost unlimited in size. We refer to this particular case as 3DoF+, meaning that the 3 degrees of freedom of camera position are limited to small offsets around the central position. Considering the problem of coordinate quantization, the impact of position error on the projection error in pixels is studied. It is shown that the projection error is proportional to the squared inverse distance of the point being projected. Consequently, a new quantization scheme based on spherical coordinates is proposed. Rate-distortion performance of the proposed method are illustrated on the well-known Garden scene. |
| title | 3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.06400 |