We present a visual-inertial depth estimation pipeline that integrates monocular depth estimation and visual-inertial odometry to produce dense depth estimates with metric scale. Our approach performs global scale and shift alignment against sparse metric depth, followed by learning-based dense alignment. We evaluate on the TartanAir and VOID datasets, observing up to 30% reduction in inverse RMSE with dense scale alignment relative to performing just global alignment alone. Our approach is especially competitive at low density; with just 150 sparse metric depth points, our dense-to-dense depth alignment method achieves over 50% lower iRMSE over sparse-to-dense depth completion by KBNet, currently the state of the art on VOID. We demonstrate successful zero-shot transfer from synthetic TartanAir to real-world VOID data and perform generalization tests on NYUv2 and VCU-RVI. Our approach is modular and is compatible with a variety of monocular depth estimation models. Video: https://youtu.be/IMwiKwSpshQ Code: https://github.com/isl-org/VI-Depth

翻译：我们提出了一种融合单目深度估计与视觉-惯性里程计的视觉-惯性深度估计流程，可生成具有度量尺度的高密度深度估计。该方法首先针对稀疏度量深度进行全局尺度与偏移对齐，随后执行基于学习的密集对齐。在TartanAir和VOID数据集上的评估表明，相较于仅进行全局对齐，采用密集尺度对齐后逆均方根误差（iRMSE）降低达30%。该方法在低稀疏度场景下表现尤为突出：仅需150个稀疏度量深度点，其密集到密集深度对齐方法相比当前VOID数据集上最先进的KBNet稀疏到密集深度补全方法，iRMSE降低超过50%。我们成功实现了从合成数据集TartanAir到真实世界VOID数据的零样本迁移，并在NYUv2和VCU-RVI数据集上进行了泛化测试。该方法具有模块化特性，兼容多种单目深度估计模型。视频链接：https://youtu.be/IMwiKwSpshQ 代码仓库：https://github.com/isl-org/VI-Depth