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 2405.03633cs.CVcs.RO
收藏

Neural Graph Map:融合高效回环检测的稠密建图

Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration

KTH Royal Institute of Technology(瑞典皇家理工学院);TU Graz(格拉茨工业大学)

Leonard Bruns, Jun Zhang, Patric Jensfelt

AI总结:

提出Neural Graph Map框架,将场景表示为动态锚定于稀疏视觉SLAM位姿图的轻量级神经场集合,实现高效回环约束整合,在建筑规模大场景的建图质量与运行时间上优于现有方法。

摘要:

基于神经场的SLAM方法通常采用单一的整体场作为场景表示。这阻碍了回环约束的有效融入,并限制了可扩展性。为解决这些缺陷,我们提出了一种新颖的RGB-D神经建图框架,其中场景由一组轻量级神经场表示,这些神经场被动态锚定到稀疏视觉SLAM系统的位姿图上。我们的方法展现出整合大规模回环的能力,且仅需最小的重新整合。此外,我们通过在优化过程中考虑多次回环,成功演示了建筑规模的建图,验证了方法的可扩展性,并表明在质量和运行时间上,该方法在大场景中优于现有最先进方法。代码开源于https://github.com/KTH-RPL/neural_graph_mapping。

英文摘要:

Neural field-based SLAM methods typically employ a single, monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a novel RGB-D neural mapping framework in which the scene is represented by a collection of lightweight neural fields which are dynamically anchored to the pose graph of a sparse visual SLAM system. Our approach shows the ability to integrate large-scale loop closures, while requiring only minimal reintegration. Furthermore, we verify the scalability of our approach by demonstrating successful building-scale mapping taking multiple loop closures into account during the optimization, and show that our method outperforms existing state-of-the-art approaches on large scenes in terms of quality and runtime. Our code is available open-source at https://github.com/KTH-RPL/neural_graph_mapping.

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。

↑