SOLVR:面向子图的激光雷达-视觉重定位
SOLVR: Submap Oriented LiDAR-Visual Re-Localisation
AI总结:
SOLVR提出统一的激光雷达-视觉重定位流程,通过立体深度预测、概率占据融合、灵活正样本定义和加权最小二乘配准,在KITTI及KITTI360上实现最先进的地点识别与远距离配准精度。
摘要:
本文提出了SOLVR,一个用于基于学习的激光雷达-视觉重定位的统一流程,该流程能够跨传感器模态执行地点识别和6自由度配准。我们提出了一种策略,通过利用立体图像流生成带有位姿信息的度量深度预测,随后使用概率占据框架融合局部窗口内的多个场景视图,以扩展相机有限的视场,从而对齐输入的传感器模态。此外,SOLVR对不同训练损失中正样本的构成采用了灵活的定义,使我们能够同时优化地点识别和配准性能。进一步地,我们用一种配准函数替代了RANSAC,该函数利用稀疏关键点对应关系的估计内点似然对简单最小二乘拟合进行加权,从而在查询与检索地点之间内点比例较低的场景中提升性能。我们在KITTI和KITTI360数据集上的实验表明,SOLVR在激光雷达-视觉地点识别和配准方面达到了最先进的性能,尤其是在查询与检索地点之间距离较大的情况下显著提高了配准精度。
英文摘要:
This paper proposes SOLVR, a unified pipeline for learning based LiDAR-Visual re-localisation which performs place recognition and 6-DoF registration across sensor modalities. We propose a strategy to align the input sensor modalities by leveraging stereo image streams to produce metric depth predictions with pose information, followed by fusing multiple scene views from a local window using a probabilistic occupancy framework to expand the limited field-of-view of the camera. Additionally, SOLVR adopts a flexible definition of what constitutes positive examples for different training losses, allowing us to simultaneously optimise place recognition and registration performance. Furthermore, we replace RANSAC with a registration function that weights a simple least-squares fitting with the estimated inlier likelihood of sparse keypoint correspondences, improving performance in scenarios with a low inlier ratio between the query and retrieved place. Our experiments on the KITTI and KITTI360 datasets show that SOLVR achieves state-of-the-art performance for LiDAR-Visual place recognition and registration, particularly improving registration accuracy over larger distances between the query and retrieved place.
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。