2025-08-06 ハーバード大学
＜関連情報＞
- https://seas.harvard.edu/news/2025/08/building-3d-scenes-2d-images-instant
- https://arxiv.org/abs/2502.04640
凸最適化によるローマ建設 Building Rome with Convex Optimization
Haoyu Han, Heng Yang
arXiv Published:last revised 1 Jul 2025 (this version, v4)
DOI:https://doi.org/10.48550/arXiv.2502.04640
Abstract
Global bundle adjustment is made easy by depth prediction and convex optimization. We (i) propose a scaled bundle adjustment (SBA) formulation that lifts 2D keypoint measurements to 3D with learned depth, (ii) design an empirically tight convex semidfinite program (SDP) relaxation that solves SBA to certfiable global optimality, (iii) solve the SDP relaxations at extreme scale with Burer-Monteiro factorization and a CUDA-based trust-region Riemannian optimizer (dubbed XM), (iv) build a structure from motion (SfM) pipeline with XM as the optimization engine and show that XM-SfM compares favorably with existing pipelines in terms of reconstruction quality while being significantly faster, more scalable, and initialization-free.
