LandMarkSystem Technical Report
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908288137822208 |
|---|---|
| author | Ma, Zhenxiang Yang, Zhenyu Tao, Miao Zhou, Yuanzhen He, Zeyu Zhang, Yuchang Fu, Rong Li, Hengjie |
| author_facet | Ma, Zhenxiang Yang, Zhenyu Tao, Miao Zhou, Yuanzhen He, Zeyu Zhang, Yuchang Fu, Rong Li, Hengjie |
| contents | 3D reconstruction is vital for applications in autonomous driving, virtual reality, augmented reality, and the metaverse. Recent advancements such as Neural Radiance Fields(NeRF) and 3D Gaussian Splatting (3DGS) have transformed the field, yet traditional deep learning frameworks struggle to meet the increasing demands for scene quality and scale. This paper introduces LandMarkSystem, a novel computing framework designed to enhance multi-scale scene reconstruction and rendering. By leveraging a componentized model adaptation layer, LandMarkSystem supports various NeRF and 3DGS structures while optimizing computational efficiency through distributed parallel computing and model parameter offloading. Our system addresses the limitations of existing frameworks, providing dedicated operators for complex 3D sparse computations, thus facilitating efficient training and rapid inference over extensive scenes. Key contributions include a modular architecture, a dynamic loading strategy for limited resources, and proven capabilities across multiple representative algorithms.This comprehensive solution aims to advance the efficiency and effectiveness of 3D reconstruction tasks.To facilitate further research and collaboration, the source code and documentation for the LandMarkSystem project are publicly available in an open-source repository, accessing the repository at: https://github.com/InternLandMark/LandMarkSystem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LandMarkSystem Technical Report Ma, Zhenxiang Yang, Zhenyu Tao, Miao Zhou, Yuanzhen He, Zeyu Zhang, Yuchang Fu, Rong Li, Hengjie Computer Vision and Pattern Recognition 3D reconstruction is vital for applications in autonomous driving, virtual reality, augmented reality, and the metaverse. Recent advancements such as Neural Radiance Fields(NeRF) and 3D Gaussian Splatting (3DGS) have transformed the field, yet traditional deep learning frameworks struggle to meet the increasing demands for scene quality and scale. This paper introduces LandMarkSystem, a novel computing framework designed to enhance multi-scale scene reconstruction and rendering. By leveraging a componentized model adaptation layer, LandMarkSystem supports various NeRF and 3DGS structures while optimizing computational efficiency through distributed parallel computing and model parameter offloading. Our system addresses the limitations of existing frameworks, providing dedicated operators for complex 3D sparse computations, thus facilitating efficient training and rapid inference over extensive scenes. Key contributions include a modular architecture, a dynamic loading strategy for limited resources, and proven capabilities across multiple representative algorithms.This comprehensive solution aims to advance the efficiency and effectiveness of 3D reconstruction tasks.To facilitate further research and collaboration, the source code and documentation for the LandMarkSystem project are publicly available in an open-source repository, accessing the repository at: https://github.com/InternLandMark/LandMarkSystem. |
| title | LandMarkSystem Technical Report |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21364 |