Monocular Visual Odometry
18 papers with code • 0 benchmarks • 5 datasets
Benchmarks
These leaderboards are used to track progress in Monocular Visual Odometry
Datasets
TUM monoVO
EndoSLAM
ConsInv Dataset
Drunkard's Dataset
Bike and Car Odometer Dataset ! Speedometer OCR
Most implemented papers
DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
ChiWeiHsiao/DeepVO-pytorch
•
•
This paper presents a novel end-to-end framework for monocular VO by using deep Recurrent Convolutional Neural Networks (RCNNs).
Visual Odometry Revisited: What Should Be Learnt?
In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning.
DF-VO: What Should Be Learnt for Visual Odometry?
More surprisingly, they show that the well-trained networks enable scale-consistent predictions over long videos, while the accuracy is still inferior to traditional methods because of ignoring geometric information.
Unsupervised Scale-consistent Depth Learning from Video
We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time.
Sparse Representations for Object and Ego-motion Estimation in Dynamic Scenes
Dynamic scenes that contain both object motion and egomotion are a challenge for monocular visual odometry (VO).
Extending Monocular Visual Odometry to Stereo Camera Systems by Scale Optimization
This paper proposes a novel approach for extending monocular visual odometry to a stereo camera system.
EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner
The codes and the link for the dataset are publicly available at https://github. com/CapsuleEndoscope/EndoSLAM.
WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks
CIFASIS/wganvo
•
•
In this work we present WGANVO, a Deep Learning based monocular Visual Odometry method.
OV$^{2}$SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications
Many applications of Visual SLAM, such as augmented reality, virtual reality, robotics or autonomous driving, require versatile, robust and precise solutions, most often with real-time capability.
Instant Visual Odometry Initialization for Mobile AR
However, standard visual odometry or SLAM algorithms require motion parallax to initialize (see Figure 1) and, therefore, suffer from delayed initialization.
