SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views
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_ | 1866916362065018880 |
|---|---|
| author | Xu, Chao Li, Ang Chen, Linghao Liu, Yulin Shi, Ruoxi Su, Hao Liu, Minghua |
| author_facet | Xu, Chao Li, Ang Chen, Linghao Liu, Yulin Shi, Ruoxi Su, Hao Liu, Minghua |
| contents | Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that may not align with users' expectations. In this paper, we explore an important scenario in which the input consists of one or a few unposed 2D images of a single object, with little or no overlap. We propose a novel method, SpaRP, to reconstruct a 3D textured mesh and estimate the relative camera poses for these sparse-view images. SpaRP distills knowledge from 2D diffusion models and finetunes them to implicitly deduce the 3D spatial relationships between the sparse views. The diffusion model is trained to jointly predict surrogate representations for camera poses and multi-view images of the object under known poses, integrating all information from the input sparse views. These predictions are then leveraged to accomplish 3D reconstruction and pose estimation, and the reconstructed 3D model can be used to further refine the camera poses of input views. Through extensive experiments on three datasets, we demonstrate that our method not only significantly outperforms baseline methods in terms of 3D reconstruction quality and pose prediction accuracy but also exhibits strong efficiency. It requires only about 20 seconds to produce a textured mesh and camera poses for the input views. Project page: https://chaoxu.xyz/sparp. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10195 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views Xu, Chao Li, Ang Chen, Linghao Liu, Yulin Shi, Ruoxi Su, Hao Liu, Minghua Computer Vision and Pattern Recognition Artificial Intelligence Graphics Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that may not align with users' expectations. In this paper, we explore an important scenario in which the input consists of one or a few unposed 2D images of a single object, with little or no overlap. We propose a novel method, SpaRP, to reconstruct a 3D textured mesh and estimate the relative camera poses for these sparse-view images. SpaRP distills knowledge from 2D diffusion models and finetunes them to implicitly deduce the 3D spatial relationships between the sparse views. The diffusion model is trained to jointly predict surrogate representations for camera poses and multi-view images of the object under known poses, integrating all information from the input sparse views. These predictions are then leveraged to accomplish 3D reconstruction and pose estimation, and the reconstructed 3D model can be used to further refine the camera poses of input views. Through extensive experiments on three datasets, we demonstrate that our method not only significantly outperforms baseline methods in terms of 3D reconstruction quality and pose prediction accuracy but also exhibits strong efficiency. It requires only about 20 seconds to produce a textured mesh and camera poses for the input views. Project page: https://chaoxu.xyz/sparp. |
| title | SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2408.10195 |