Gaussian Object Carver: Object-Compositional Gaussian Splatting with surfaces completion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929611567267840 |
|---|---|
| author | Liu, Liu Wang, Xinjie Qiu, Jiaxiong Lin, Tianwei Zhou, Xiaolin Su, Zhizhong |
| author_facet | Liu, Liu Wang, Xinjie Qiu, Jiaxiong Lin, Tianwei Zhou, Xiaolin Su, Zhizhong |
| contents | 3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in scenarios requiring high interactivity and object-level manipulation. In this paper, we introduce the Gaussian Object Carver (GOC), a novel, efficient, and scalable framework for object-compositional 3D scene reconstruction. GOC leverages 3D Gaussian Splatting (GS), enriched with monocular geometry priors and multi-view geometry regularization, to achieve high-quality and flexible reconstruction. Furthermore, we propose a zero-shot Object Surface Completion (OSC) model, which uses 3D priors from 3d object data to reconstruct unobserved surfaces, ensuring object completeness even in occluded areas. Experimental results demonstrate that GOC improves reconstruction efficiency and geometric fidelity. It holds promise for advancing the practical application of digital twins in embodied AI, AR/VR, and interactive simulation environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02075 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Gaussian Object Carver: Object-Compositional Gaussian Splatting with surfaces completion Liu, Liu Wang, Xinjie Qiu, Jiaxiong Lin, Tianwei Zhou, Xiaolin Su, Zhizhong Computer Vision and Pattern Recognition Robotics 3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in scenarios requiring high interactivity and object-level manipulation. In this paper, we introduce the Gaussian Object Carver (GOC), a novel, efficient, and scalable framework for object-compositional 3D scene reconstruction. GOC leverages 3D Gaussian Splatting (GS), enriched with monocular geometry priors and multi-view geometry regularization, to achieve high-quality and flexible reconstruction. Furthermore, we propose a zero-shot Object Surface Completion (OSC) model, which uses 3D priors from 3d object data to reconstruct unobserved surfaces, ensuring object completeness even in occluded areas. Experimental results demonstrate that GOC improves reconstruction efficiency and geometric fidelity. It holds promise for advancing the practical application of digital twins in embodied AI, AR/VR, and interactive simulation environments. |
| title | Gaussian Object Carver: Object-Compositional Gaussian Splatting with surfaces completion |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2412.02075 |