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 1708.00783cs.CV
收藏

InfiniTAM v3:一个基于环闭合的大规模三维重建框架

InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure

University of Oxford(牛津大学);Samsung Research America(三星美国研究院)

Victor Adrian Prisacariu, Olaf Kähler, Stuart Golodetz, Michael Sapienza, Tommaso Cavallari, Philip H S Torr, David W Murray

摘要:

近年来,体模型已经成为3D场景的流行表示。导致其流行的一个突破是KinectFusion,它专注于使用RGB-D传感器进行3D重建。然而,单目SLAM也已经用非常类似的方法来解决。将重建体表示为TSDF导致了这些系统的GPU实现可以实现的大部分简单性和效率。然而,这种表示是内存密集型的,并限制了小规模重建的适用性。已经探索了几种途径来克服这一问题。为了总结它们并提供快速,灵活的3D重建管道,我们提出了一个新的,统一的框架,称为InfiniTAM。其想法是,相机跟踪、场景表示和新数据集成等步骤可以轻松替换并适应用户的需求。本报告描述了InfiniTAM v3(我们的InfiniTAM系统的第三个版本)的技术实施细节。我们添加了各种新功能,并对低级代码进行了大量增强,从而显着提高了我们的相机跟踪性能。我们期望最感兴趣的新功能是(i)一个强大的相机跟踪模块;(ii)Glocker等人的实现。的关键帧为基础的随机蕨类植物相机relocaliser;(iii)一种新的方法,以全球一致的TSDF为基础的重建,划分成刚性的子地图和优化它们之间的相对姿态的基础上,和(iv)凯勒等人的实施。的基于冲浪的重建方法。

英文摘要:

Volumetric models have become a popular representation for 3D scenes in recent years. One breakthrough leading to their popularity was KinectFusion, which focuses on 3D reconstruction using RGB-D sensors. However, monocular SLAM has since also been tackled with very similar approaches. Representing the reconstruction volumetrically as a TSDF leads to most of the simplicity and efficiency that can be achieved with GPU implementations of these systems. However, this representation is memory-intensive and limits applicability to small-scale reconstructions. Several avenues have been explored to overcome this. With the aim of summarizing them and providing for a fast, flexible 3D reconstruction pipeline, we propose a new, unifying framework called InfiniTAM. The idea is that steps like camera tracking, scene representation and integration of new data can easily be replaced and adapted to the user's needs. This report describes the technical implementation details of InfiniTAM v3, the third version of our InfiniTAM system. We have added various new features, as well as making numerous enhancements to the low-level code that significantly improve our camera tracking performance. The new features that we expect to be of most interest are (i) a robust camera tracking module; (ii) an implementation of Glocker et al.'s keyframe-based random ferns camera relocaliser; (iii) a novel approach to globally-consistent TSDF-based reconstruction, based on dividing the scene into rigid submaps and optimising the relative poses between them; and (iv) an implementation of Keller et al.'s surfel-based reconstruction approach.

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。

↑