VIMD: Monocular Visual-Inertial Motion and Depth Estimation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917261951893504 |
|---|---|
| author | Katragadda, Saimouli Huang, Guoquan |
| author_facet | Katragadda, Saimouli Huang, Guoquan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19713 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VIMD: Monocular Visual-Inertial Motion and Depth Estimation Katragadda, Saimouli Huang, Guoquan Computer Vision and Pattern Recognition Robotics 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. |
| title | VIMD: Monocular Visual-Inertial Motion and Depth Estimation |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2509.19713 |