arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.03134cs.CVcs.DC
收藏

图处理机上的光束平差

Bundle Adjustment on a Graph Processor

Imperial College London(帝国理工学院);Graphcore

Joseph Ortiz, Mark Pupilli, Stefan Leutenegger, Andrew J. Davison

摘要:

图形处理器(如Graphcore的智能处理单元(IPU))是人工智能的新型计算机体系结构的主要新浪潮的一部分,具有大规模并行计算、分布式片上存储器和非常高的核间通信带宽的通用设计,这使得任意图形上的消息传递算法具有突破性的性能。我们第一次表明,经典的计算机视觉问题的光束法平差(BA)可以非常快速地解决图形处理器使用高斯置信传播。我们简单但完全并行的实现使用单个IPU芯片上的1216个内核,例如,在40 ms内解决125个关键帧和1919个点的真正BA问题,而Ceres CPU库的时间为1450 ms。进一步的代码优化肯定会增加静态问题的差异,但我们认为,图处理的真正希望是对代表空间AI问题的一般动态变化因子图进行灵活的就地优化。我们给出的实验表明,GBP的能力,有效地解决增量SLAM问题,并处理强大的成本函数和不同类型的因素。

英文摘要:

Graph processors such as Graphcore's Intelligence Processing Unit (IPU) are part of the major new wave of novel computer architecture for AI, and have a general design with massively parallel computation, distributed on-chip memory and very high inter-core communication bandwidth which allows breakthrough performance for message passing algorithms on arbitrary graphs. We show for the first time that the classical computer vision problem of bundle adjustment (BA) can be solved extremely fast on a graph processor using Gaussian Belief Propagation. Our simple but fully parallel implementation uses the 1216 cores on a single IPU chip to, for instance, solve a real BA problem with 125 keyframes and 1919 points in under 40ms, compared to 1450ms for the Ceres CPU library. Further code optimisation will surely increase this difference on static problems, but we argue that the real promise of graph processing is for flexible in-place optimisation of general, dynamically changing factor graphs representing Spatial AI problems. We give indications of this with experiments showing the ability of GBP to efficiently solve incremental SLAM problems, and deal with robust cost functions and different types of factors.

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。

↑