arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.18771cs.CVcs.RO
收藏

NARUTO:基于不确定目标观测的神经主动重建

NARUTO: Neural Active Reconstruction from Uncertain Target Observations

OPPO US Research Center(OPPO美国研究中心);Clemson University(克莱姆森大学);Indiana University(印第安纳大学)

Ziyue Feng, Huangying Zhan, Zheng Chen, Qingan Yan, Xiangyu Xu, Changjiang Cai, Bing Li, Qilun Zhu, Yi Xu

AI总结:

本研究提出神经主动重建系统NARUTO,通过多分辨率哈希网格建图结合不确定性学习模块,实现高效路径规划与高保真环境重建,在基准数据集上达到SOTA水平,还可增强现有神经SLAM系统性能。

摘要:

我们提出了NARUTO——一种结合混合神经表征与不确定性学习的神经主动重建系统,可实现高保真表面重建。该方法采用多分辨率哈希网格作为建图骨干网络,选择它的原因是其收敛速度极快,且具备捕捉高频局部特征的能力。本研究的核心是引入了一个不确定性学习模块,它能在主动重建环境的同时动态量化重建不确定性。借助学习到的不确定性,我们提出了一种新颖的不确定性聚合策略,用于目标搜索和高效路径规划。该系统以不确定观测为目标自主探索环境,能以极高的完整性和保真度完成环境重建。我们还通过一种主动光线采样策略增强了现有SOTA神经SLAM系统,以此验证了这种具备不确定性感知的方法的实用性。我们使用室内场景模拟器在多种环境中对NARUTO进行了广泛评估,结果证实其性能优越,在主动重建领域达到了SOTA水平,这一点从它在Replica和MP3D等基准数据集上的出色表现中可得到印证。

英文摘要:

We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction. Our approach leverages a multi-resolution hash-grid as the mapping backbone, chosen for its exceptional convergence speed and capacity to capture high-frequency local features.The centerpiece of our work is the incorporation of an uncertainty learning module that dynamically quantifies reconstruction uncertainty while actively reconstructing the environment. By harnessing learned uncertainty, we propose a novel uncertainty aggregation strategy for goal searching and efficient path planning. Our system autonomously explores by targeting uncertain observations and reconstructs environments with remarkable completeness and fidelity. We also demonstrate the utility of this uncertainty-aware approach by enhancing SOTA neural SLAM systems through an active ray sampling strategy. Extensive evaluations of NARUTO in various environments, using an indoor scene simulator, confirm its superior performance and state-of-the-art status in active reconstruction, as evidenced by its impressive results on benchmark datasets like Replica and MP3D.

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。

↑