Heng Yang (@hankyang94)
2025-05-14 | ❤️ 289 | 🔁 44
“Building Rome with Convex Optimization” has been accepted to RSS2025!
Try XM, our new structure from motion pipeline powered by GPU-accelerated convex semidefinite optimization: https://github.com/ComputationalRobotics/XM-code
XM solves large-scale (nonconvex) global bundle adjustment problem via learned depth and a tight convex semidefinite relaxation.
By implementing the Burer-Monteiro low-rank factorization algorithm in CUDA, XM can solve bundle adjustment problems with more than 10,000 images/views.
Technical details in the paper: https://arxiv.org/abs/2502.04640
Kudos to @Hyhan0118
🔗 원본 링크
미디어
🔗 Related
Auto-generated - needs manual review