CuSfM: CUDA-Accelerated Structure-from-Motion
This work addresses the problem of computational bottlenecks in camera pose estimation for offline processing in computer vision and robotics, offering a domain-specific incremental improvement.
The paper tackles the challenge of efficient and accurate camera pose estimation for applications like autonomous navigation and robotics by introducing cuSfM, a CUDA-accelerated offline Structure-from-Motion system that leverages GPU parallelization to improve accuracy and processing speed compared to COLMAP across various testing scenarios.
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.