CuSfM: CUDA-Accelerated Structure-from-Motion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912654045478912 |
|---|---|
| author | Yu, Jingrui Liu, Jun Ren, Kefei Biswas, Joydeep Ye, Rurui Wu, Keqiang Majithia, Chirag Zeng, Di |
| author_facet | Yu, Jingrui Liu, Jun Ren, Kefei Biswas, Joydeep Ye, Rurui Wu, Keqiang Majithia, Chirag Zeng, Di |
| contents | Efficient and accurate camera pose estimation forms the foundational requirement for dense reconstruction in autonomous navigation, robotic perception, and virtual simulation systems. This paper addresses the challenge via cuSfM, a CUDA-accelerated offline Structure-from-Motion system that leverages GPU parallelization to efficiently employ computationally intensive yet highly accurate feature extractors, generating comprehensive and non-redundant data associations for precise camera pose estimation and globally consistent mapping. The system supports pose optimization, mapping, prior-map localization, and extrinsic refinement. It is designed for offline processing, where computational resources can be fully utilized to maximize accuracy. Experimental results demonstrate that cuSfM achieves significantly improved accuracy and processing speed compared to the widely used COLMAP method across various testing scenarios, while maintaining the high precision and global consistency essential for offline SfM applications. The system is released as an open-source Python wrapper implementation, PyCuSfM, available at https://github.com/nvidia-isaac/pyCuSFM, to facilitate research and applications in computer vision and robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15271 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CuSfM: CUDA-Accelerated Structure-from-Motion Yu, Jingrui Liu, Jun Ren, Kefei Biswas, Joydeep Ye, Rurui Wu, Keqiang Majithia, Chirag Zeng, Di Computer Vision and Pattern Recognition Robotics Efficient and accurate camera pose estimation forms the foundational requirement for dense reconstruction in autonomous navigation, robotic perception, and virtual simulation systems. This paper addresses the challenge via cuSfM, a CUDA-accelerated offline Structure-from-Motion system that leverages GPU parallelization to efficiently employ computationally intensive yet highly accurate feature extractors, generating comprehensive and non-redundant data associations for precise camera pose estimation and globally consistent mapping. The system supports pose optimization, mapping, prior-map localization, and extrinsic refinement. It is designed for offline processing, where computational resources can be fully utilized to maximize accuracy. Experimental results demonstrate that cuSfM achieves significantly improved accuracy and processing speed compared to the widely used COLMAP method across various testing scenarios, while maintaining the high precision and global consistency essential for offline SfM applications. The system is released as an open-source Python wrapper implementation, PyCuSfM, available at https://github.com/nvidia-isaac/pyCuSFM, to facilitate research and applications in computer vision and robotics. |
| title | CuSfM: CUDA-Accelerated Structure-from-Motion |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2510.15271 |