arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00446cs.CV
收藏

随机光束法平差实现高效可扩展的三维重建

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

Hong Kong University of Science and Technology(香港科技大学);Everest Innovation Technology(珠峰创新科技)

Lei Zhou, Zixin Luo, Mingmin Zhen, Tianwei Shen, Shiwei Li, Zhuofei Huang, Tian Fang, Long Quan

摘要:

目前的光束法平差求解器,如Levenberg-Marquardt(LM)算法是有限的瓶颈,在解决减少相机系统(RCS)的尺寸是成比例的相机数量。当问题被放大时,这个步骤在计算上既不高效,也不适合单个计算节点。在这项工作中,我们提出了一个随机光束法平差算法,旨在分解的RCS近似内部的LM迭代,以提高效率和可扩展性。它首先重新制定的LM迭代的二次规划问题的聚类的可视性图通过引入跨类的等式约束。然后,我们建议将其松弛成一个机会约束问题,并通过抽样凸规划来解决它。松弛的目的是消除集群之间的相互依赖性体现的约束,使一个大的RCS可以分解成独立的线性子问题。在无序互联网图像集和序列SLAM图像集上的数值实验以及在大规模数据集上的分布式实验表明了该方法的高效性和可扩展性。代码发布于https://github.com/zlthinker/STBA。

英文摘要:

Current bundle adjustment solvers such as the Levenberg-Marquardt (LM) algorithm are limited by the bottleneck in solving the Reduced Camera System (RCS) whose dimension is proportional to the camera number. When the problem is scaled up, this step is neither efficient in computation nor manageable for a single compute node. In this work, we propose a stochastic bundle adjustment algorithm which seeks to decompose the RCS approximately inside the LM iterations to improve the efficiency and scalability. It first reformulates the quadratic programming problem of an LM iteration based on the clustering of the visibility graph by introducing the equality constraints across clusters. Then, we propose to relax it into a chance constrained problem and solve it through sampled convex program. The relaxation is intended to eliminate the interdependence between clusters embodied by the constraints, so that a large RCS can be decomposed into independent linear sub-problems. Numerical experiments on unordered Internet image sets and sequential SLAM image sets, as well as distributed experiments on large-scale datasets, have demonstrated the high efficiency and scalability of the proposed approach. Codes are released at https://github.com/zlthinker/STBA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑