ViPR: Visual-Odometry-Aided Pose Regression for 6DoF Camera Localization
Abstract
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly from (a series of) images or by merging depth maps with optical flow (OF), research that combines absolute pose regression with OF is limited.We propose ViPR, a novel modular architecture for longterm 6DoF VO that leverages temporal information and synergies between absolute pose estimates (from PoseNet-like modules) and relative pose estimates (from FlowNet-based modules) by combining both through recurrent layers. Experiments on known datasets and on our own Industry dataset show that our modular design outperforms state ofthe art in long-term navigation tasks.
Cite
Text
Ott et al. "ViPR: Visual-Odometry-Aided Pose Regression for 6DoF Camera Localization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00029Markdown
[Ott et al. "ViPR: Visual-Odometry-Aided Pose Regression for 6DoF Camera Localization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/ott2020cvprw-vipr/) doi:10.1109/CVPRW50498.2020.00029BibTeX
@inproceedings{ott2020cvprw-vipr,
title = {{ViPR: Visual-Odometry-Aided Pose Regression for 6DoF Camera Localization}},
author = {Ott, Felix and Feigl, Tobias and Löffler, Christoffer and Mutschler, Christopher},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {187-198},
doi = {10.1109/CVPRW50498.2020.00029},
url = {https://mlanthology.org/cvprw/2020/ott2020cvprw-vipr/}
}