BEV-DWPVO：基于BEV的可微加权Procrustes用于地面低尺度漂移单目视觉里程计
BEV-DWPVO: BEV-based Differentiable Weighted Procrustes for Low Scale-drift Monocular Visual Odometry on Ground
AI总结：
提出BEV-DWPVO单目视觉里程计系统，利用地面假设和鸟瞰图特征将位姿估计从6自由度降至3自由度，通过可微加权Procrustes求解器实现低尺度漂移，在NCLT、Oxford和KITTI数据集上优于现有方法。
摘要：
单目视觉里程计（MVO）为自动驾驶车辆提供了一种经济高效、实时的定位解决方案。然而，MVO系统普遍面临单目相机缺乏固有尺度信息的问题。传统方法具有良好的可解释性，但只能获得相对尺度，且在长距离任务中遭受严重的尺度漂移。透视视图下基于学习的方法利用大量训练数据获取先验知识，并通过预测深度值来估计绝对尺度。然而，由于需要准确估计每个点的深度，其泛化能力受限。相比之下，我们提出了一种新颖的MVO系统，称为BEV-DWPVO。我们的方法利用地面平面的常见假设，使用鸟瞰图（BEV）特征图以网格化结构和统一尺度表示环境。这使我们能够将位姿估计的复杂度从6自由度（DoF）降低到3自由度。在BEV空间内提取并匹配关键点，随后通过可微加权Procrustes求解器进行位姿估计。整个系统完全可微，支持仅使用位姿监督的端到端训练，无需辅助任务。我们在具有挑战性的长序列数据集NCLT、Oxford和KITTI上验证了BEV-DWPVO，在大多数评估指标上取得了优于现有MVO方法的结果。
英文摘要：
Monocular Visual Odometry (MVO) provides a cost-effective, real-time positioning solution for autonomous vehicles. However, MVO systems face the common issue of lacking inherent scale information from monocular cameras. Traditional methods have good interpretability but can only obtain relative scale and suffer from severe scale drift in long-distance tasks. Learning-based methods under perspective view leverage large amounts of training data to acquire prior knowledge and estimate absolute scale by predicting depth values. However, their generalization ability is limited due to the need to accurately estimate the depth of each point. In contrast, we propose a novel MVO system called BEV-DWPVO. Our approach leverages the common assumption of a ground plane, using Bird's-Eye View (BEV) feature maps to represent the environment in a grid-based structure with a unified scale. This enables us to reduce the complexity of pose estimation from 6 Degrees of Freedom (DoF) to 3-DoF. Keypoints are extracted and matched within the BEV space, followed by pose estimation through a differentiable weighted Procrustes solver. The entire system is fully differentiable, supporting end-to-end training with only pose supervision and no auxiliary tasks. We validate BEV-DWPVO on the challenging long-sequence datasets NCLT, Oxford, and KITTI, achieving superior results over existing MVO methods on most evaluation metrics.
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。
