VIMD：单目视觉-惯性运动和深度估计
VIMD: Monocular Visual-Inertial Motion and Depth Estimation
AI总结：
VIMD通过多视图信息迭代优化像素尺度，实现高效且鲁棒的单目视觉-惯性深度估计，适用于资源受限的3D视觉感知场景。
摘要：
准确且高效的密集度量深度估计对于机器人和XR中的3D视觉感知至关重要。在本文中，我们开发了一个单目视觉-惯性运动和深度（VIMD）学习框架，通过利用准确且高效的基于MSCKF的单目视觉-惯性运动跟踪来估计密集度量深度。VIMD的核心是利用多视图信息迭代细化每个像素的尺度，而不是像先前工作那样全局拟合一个不变的仿射模型。VIMD框架高度模块化，使其能够与各种现有的深度估计骨干网络兼容。我们在TartanAir和VOID数据集上进行了广泛的评估，并在AR Table数据集上展示了其零样本泛化能力。我们的结果表明，VIMD在极稀疏的点情况下（每张图像仅有10-20个度量深度点）也能实现卓越的准确性和鲁棒性。这使得所提出的VIMD成为在资源受限环境下部署的实用解决方案，同时其鲁棒性能和强大的泛化能力在广泛的应用场景中具有显著潜力。
英文摘要：
Accurate and efficient dense metric depth estimation is crucial for 3D visual perception in robotics and XR. In this paper, we develop a monocular visual-inertial motion and depth (VIMD) learning framework to estimate dense metric depth by leveraging accurate and efficient MSCKF-based monocular visual-inertial motion tracking. At the core the proposed VIMD is to exploit multi-view information to iteratively refine per-pixel scale, instead of globally fitting an invariant affine model as in the prior work. The VIMD framework is highly modular, making it compatible with a variety of existing depth estimation backbones. We conduct extensive evaluations on the TartanAir and VOID datasets and demonstrate its zero-shot generalization capabilities on the AR Table dataset. Our results show that VIMD achieves exceptional accuracy and robustness, even with extremely sparse points as few as 10-20 metric depth points per image. This makes the proposed VIMD a practical solution for deployment in resource constrained settings, while its robust performance and strong generalization capabilities offer significant potential across a wide range of scenarios.
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。
