Robust Visual Odometry Using Position-Aware Flow and Geometric Bundle Adjustment
@article{Cao2021RobustVO, title={Robust Visual Odometry Using Position-Aware Flow and Geometric Bundle Adjustment}, author={Yijun Cao and Xian-Shi Zhang and Fuya Luo and Peng Peng and Yongjie Li}, journal={ArXiv}, year={2021}, volume={abs/2111.11141} }
In this paper, an essential problem of robust visual odometry (VO) is approached by incorporating geometry-based methods into deep-learning architecture in a self-supervised manner. Generally, pure geometry-based algorithms are not as robust as deep learning in feature-point extraction and matching, but perform well in ego-motion estimation because of their well-established geometric theory. In this work, a novel optical flow network (PANet) built on a position-aware mechanism is proposed first…
No Paper Link Available
Figures and Tables from this paper
2 Citations
A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimation
- Computer ScienceArXiv
- 2022
This paper presents a multi-task scheme that achieves mutual assistance by means of the Flow to Depth (F2D), Depth to Flow (D2F), and Exponential Moving Average (EMA).
Unsupervised Vision and Vision-motion Calibration Strategies for PointGoal Navigation in Indoor Environment
- Computer ScienceArXiv
- 2022
Novel vision and vision- motion calibration strategies to train visual and motion path integration in unsupervised manner and outperforms the partially supervised learning algorithms on the popular Gibson dataset are proposed.
References
SHOWING 1-10 OF 61 REFERENCES
Direct Sparse Odometry
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine Intelligence
- 2018
The experiments show that the presented approach significantly outperforms state-of-the-art direct and indirect methods in a variety of real-world settings, both in terms of tracking accuracy and robustness.
Visual Odometry Revisited: What Should Be Learnt?
- Computer Science2020 IEEE International Conference on Robotics and Automation (ICRA)
- 2020
This work revisit the basics of VO and explore the right way for integrating deep learning with epipolar geometry and Perspective-n-Point method and design a simple but robust frame-to-frame VO algorithm (DF-VO) which outperforms pure deep learning-based and geometry-based methods.
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
- Computer Science2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
An adaptive geometric consistency loss is proposed to increase robustness towards outliers and non-Lambertian regions, which resolves occlusions and texture ambiguities effectively and achieves state-of-the-art results in all of the three tasks, performing better than previously unsupervised methods and comparably with supervised ones.
Self-Supervised Learning With Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera
- Computer Science2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
We present GLNet, a self-supervised framework for learning depth, optical flow, camera pose and intrinsic parameters from monocular video -- addressing the difficulty of acquiring realistic…
Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints
- Computer Science2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
The main contribution is to explicitly consider the inferred 3D geometry of the whole scene, and enforce consistency of the estimated 3D point clouds and ego-motion across consecutive frames, and outperforms the state-of-the-art for both breadth and depth.
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
- Computer ScienceNeurIPS
- 2019
This paper proposes a geometry consistency loss for scale-consistent predictions and an induced self-discovered mask for handling moving objects and occlusions and is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale- Consistent camera trajectories over a long video sequence.
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
- Computer Science2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization.
Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias, and Rolling Shutter Effect
- Computer ScienceIEEE Robotics and Automation Letters
- 2018
This work evaluates three very influential yet easily overlooked aspects of photometric calibration, motion bias, and rolling shutter effect quantitatively on the state of the art of direct, feature-based, and semi-direct methods, providing the community with useful practical knowledge both for better applying existing methods and developing new algorithms of VO and SLAM.
Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling
- Computer ScienceECCV
- 2020
This paper model the long-term dependency in pose prediction using a pose network that features a two-layer convolutional LSTM module, and proposes a stage-wise training mechanism, where the first stage operates in a local time window and the second stage refines the poses with a "global" loss given the firststage features.
3D Packing for Self-Supervised Monocular Depth Estimation
- Computer Science2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
This work proposes a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos, which outperforms other self, semi, and fully supervised methods on the KITTI benchmark.