DROID-ANCHOR：基于里程计锚定的循环度量深度估计
DROID-ANCHOR: Odometry-Anchored Recurrent Metric Depth Estimation
- UC Berkeley（加州大学伯克利分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对单目系统尺度问题，提出Metric-DROID架构，通过集成里程计，利用LSTM更新算子、不确定性感知度量后端及选择性残差微调策略，实现视觉SLAM与物理现实锚定，有效解决尺度模糊等问题。
AI中文摘要：
精确的度量深度估计对自主机器人导航至关重要，但单目系统存在尺度模糊和尺度漂移问题。尽管基于循环流的SLAM系统具有很强的鲁棒性，但仍存在尺度模糊。本文提出Metric-DROID，一种通过集成本体感受里程计将视觉SLAM锚定到物理现实的端到端循环架构。该框架有以下创新：一是LSTM更新算子，将高频里程计序列编码到空间特征图中；二是不确定性感知度量后端，将里程计视为具有学习到的异方差协方差的几何锚；三是选择性残差微调策略，既能保留预训练几何先验又能实现零射击度量对齐。
英文摘要：
Precise metric depth estimation is fundamental for autonomous robot navigation, yet monocular systems inherently suffer from scale ambiguity and scale drift. While recent recurrent flow-based SLAM systems have demonstrated state-of-the-art robustness, they remain scale-ambiguous. In this paper, we propose Metric-DROID, an end-to-end recurrent architecture that anchors visual SLAM to physical reality by integrating proprioceptive odometry. Our framework introduces the following innovations: (1) A LSTM Update Operator that encodes high-frequency odometry sequences into spatial feature maps, providing a persistent metric bias for iterative refinement. (2) An Uncertainty-Aware Metric Backend ($BA_{odom}$) that treats odometry as a geometric anchor with learned heteroscedastic covariance. By regressing a time-varying metric uncertainty $Σ_{o}$, our system intelligently balances visual re-projection and metric translation residuals, effectively mitigating the impact of wheel-slip and sensor noise. (3) We further propose a selective residual fine-tuning strategy to preserve pre-trained geometric priors while enabling zero-shot metric alignment.
