From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis
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_ | 1866911550742200320 |
|---|---|
| author | Huang, Ranran Luo, Weixun Mao, Ye Mikolajczyk, Krystian |
| author_facet | Huang, Ranran Luo, Weixun Mao, Ye Mikolajczyk, Krystian |
| contents | In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D Gaussians from uncalibrated and unposed context views and renders target views using its self-predicted camera parameters, enabling self-supervised training from 2D photometric supervision. To ensure stable convergence, NAS3R integrates reconstruction and camera prediction within a shared transformer backbone regulated by masked attention, and adopts a depth-based Gaussian formulation that facilitates well-conditioned optimization. The framework is compatible with state-of-the-art supervised 3D reconstruction architectures and can incorporate pretrained priors or intrinsic information when available. Extensive experiments show that NAS3R achieves superior results to other self-supervised methods, establishing a scalable and geometry-aware paradigm for 3D reconstruction from unconstrained data. Code and models are publicly available at https://ranrhuang.github.io/nas3r/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27455 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis Huang, Ranran Luo, Weixun Mao, Ye Mikolajczyk, Krystian Computer Vision and Pattern Recognition In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D Gaussians from uncalibrated and unposed context views and renders target views using its self-predicted camera parameters, enabling self-supervised training from 2D photometric supervision. To ensure stable convergence, NAS3R integrates reconstruction and camera prediction within a shared transformer backbone regulated by masked attention, and adopts a depth-based Gaussian formulation that facilitates well-conditioned optimization. The framework is compatible with state-of-the-art supervised 3D reconstruction architectures and can incorporate pretrained priors or intrinsic information when available. Extensive experiments show that NAS3R achieves superior results to other self-supervised methods, establishing a scalable and geometry-aware paradigm for 3D reconstruction from unconstrained data. Code and models are publicly available at https://ranrhuang.github.io/nas3r/. |
| title | From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27455 |