用里程计锚定视觉里程计，解决单目深度估计的尺度漂移问题。
DROID-ANCHOR: Odometry-Anchored Recurrent Metric Depth Estimation
- 用LSTM将高频里程计信息编码为空间特征，提供持续的度量偏置。
- 通过学习时变不确定性，智能平衡视觉重投影与度量位移残差。
- 零样本适配新场景，保留预训练几何先验，适合机器人导航应用。
精确的度量深度估计对自主机器人导航至关重要，但单目系统存在固有的尺度模糊性和尺度漂移问题。尽管近期基于循环光流的SLAM系统表现出最先进的鲁棒性，仍存在尺度模糊。本文提出Metric-DROID，一种端到端循环架构，通过融合本体感受里程计将视觉SLAM锚定到物理现实。创新包括：(1) 采用LSTM更新算子，将高频里程计序列编码为空间特征图，提供持续的度量偏置以支持迭代优化；(2) 提出不确定性感知的度量后端（$BA_{odom}$），将里程计视为带有学习异方差协方差的几何锚点，通过回归随时间变化的度量不确定性 $Σ_{o}$，智能平衡视觉重投影与度量平移残差，有效缓解轮滑和传感器噪声影响；(3) 进一步提出选择性残差微调策略，在保留预训练几何先验的同时实现零样本度量对齐。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。