Camera Motion Estimation from RGB-D-Inertial Scene Flow
Abstract
In this paper, we introduce a novel formulation for camera motion estimation that integrates RGB-D images and inertial data through scene flow. Our goal is to accurately estimate the camera motion in a rigid 3D environment, along with the state of the inertial measurement unit (IMU). Our proposed method offers the flexibility to operate as a multiframe optimization or to marginalize older data, thus effectively utilizing past measurements. To assess the performance of our method, we conducted evaluations using both synthetic data from the ICL-NUIM dataset and real data sequences from the OpenLORIS-Scene dataset. Our results show that the fusion of these two sensors enhances the accuracy of camera motion estimation when compared to using only visual data.
Cite
Text
Cerezo and Civera. "Camera Motion Estimation from RGB-D-Inertial Scene Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00089Markdown
[Cerezo and Civera. "Camera Motion Estimation from RGB-D-Inertial Scene Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/cerezo2024cvprw-camera/) doi:10.1109/CVPRW63382.2024.00089BibTeX
@inproceedings{cerezo2024cvprw-camera,
title = {{Camera Motion Estimation from RGB-D-Inertial Scene Flow}},
author = {Cerezo, Samuel and Civera, Javier},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2024},
pages = {841-849},
doi = {10.1109/CVPRW63382.2024.00089},
url = {https://mlanthology.org/cvprw/2024/cerezo2024cvprw-camera/}
}