Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913136656777216 |
|---|---|
| author | Zhang, Yuantai Yang, Jiaqi Zeng, Huajian Chen, Changhao Li, Haoang Li, Liang Song, Dezhen Zuo, Xingxing |
| author_facet | Zhang, Yuantai Yang, Jiaqi Zeng, Huajian Chen, Changhao Li, Haoang Li, Liang Song, Dezhen Zuo, Xingxing |
| contents | Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for subsequent state estimation. Despite steady progress, most existing methods heavily rely on visual feature correspondences and require 3-4 seconds of sensory data for successful initialization, which limits their applicability and efficiency. With the advent of feed-forward 3D models that can directly predict point clouds from images, we revisit the visual-inertial initialization problem from a concise perspective. In this work, we propose a feature-free initialization framework that leverages up-to-scale point clouds predicted by a feed-forward 3D model, thereby obviating the need for visual feature tracking and estimation. This design substantially reduces system complexity and improves the reliability of initialization. Experiments on public datasets demonstrate that the proposed feature-free initialization method achieves the highest success rate, exceeding 90%, and significantly reduces the data duration required for successful initialization, typically to under 1.2 s. We further validate our method on a self-collected dataset covering various indoor and outdoor scenarios, demonstrating robust performance, particularly in visually degraded environments where existing methods often fail. The code and dataset are available at https://github.com/Yuantai-Z/FF-VIO-Init. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17327 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model Zhang, Yuantai Yang, Jiaqi Zeng, Huajian Chen, Changhao Li, Haoang Li, Liang Song, Dezhen Zuo, Xingxing Robotics Artificial Intelligence Computer Vision and Pattern Recognition Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for subsequent state estimation. Despite steady progress, most existing methods heavily rely on visual feature correspondences and require 3-4 seconds of sensory data for successful initialization, which limits their applicability and efficiency. With the advent of feed-forward 3D models that can directly predict point clouds from images, we revisit the visual-inertial initialization problem from a concise perspective. In this work, we propose a feature-free initialization framework that leverages up-to-scale point clouds predicted by a feed-forward 3D model, thereby obviating the need for visual feature tracking and estimation. This design substantially reduces system complexity and improves the reliability of initialization. Experiments on public datasets demonstrate that the proposed feature-free initialization method achieves the highest success rate, exceeding 90%, and significantly reduces the data duration required for successful initialization, typically to under 1.2 s. We further validate our method on a self-collected dataset covering various indoor and outdoor scenarios, demonstrating robust performance, particularly in visually degraded environments where existing methods often fail. The code and dataset are available at https://github.com/Yuantai-Z/FF-VIO-Init. |
| title | Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.17327 |