# VIMD: Monocular Visual-Inertial Motion and Depth Estimation

arXiv: https://arxiv.org/abs/2509.19713 · HTML: https://mlsanity.com/paper/2509.19713/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [Unsupervised Depth Completion from Visual Inertial Odometry](https://mlsanity.com/paper/1905.08616/) (2019)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [Geo-Supervised Visual Depth Prediction](https://mlsanity.com/paper/1807.11130/) (2018)
- [Visual-Inertial Navigation: A Concise Review](https://mlsanity.com/paper/1906.02650/) (2019)
- [CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth](https://mlsanity.com/paper/2012.10133/) (2020)
- [Monocular Visual-Inertial Depth Estimation](https://mlsanity.com/paper/2303.12134/) (2023)
- [DRO: Deep Recurrent Optimizer for Video to Depth](https://mlsanity.com/paper/2103.13201/) (2021)
- [Online Language Splatting](https://mlsanity.com/paper/2503.09447/) (2025)
- [Online Self-Calibration for Visual-Inertial Navigation Systems: Models, Analysis and Degeneracy](https://mlsanity.com/paper/2201.09170/) (2022)
- [Visual-Inertial SLAM as Simple as A, B, VINS](https://mlsanity.com/paper/2406.05969/) (2024)

## Abstract (arXiv)

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.