flâneur

[2510.15271] CuSfM: CUDA-Accelerated Structure-from-Motion

arxiv.org · 6,751 words · saved by 1 readers

Abstract: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 this https URL, to facilitate research and applications in computer vision and robotics.

2025-10-20 CuSfM: CUDA-Accelerated Structure-from-Motion Jingrui Yu1 , Jun Liu1 , Kefei Ren1 , Joydeep Biswas1 , Rurui Ye1 , Keqiang Wu1 , Chirag Majithia1 , Di Zeng1* 1 NVIDIA * Project Lead {jingruiy, junli, kefeir, jbiswas, ruruiye, keqiangw, cmajithia, dizeng}@nvidia.com Abstract Efficient and…

saved by

related reading