Benchmarks
Greatest papers with code
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.
DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
This paper presents a novel end-to-end framework for monocular VO by using deep Recurrent Convolutional Neural Networks (RCNNs).
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.
DEPTH ESTIMATION MONOCULAR VISUAL ODOMETRY POSE ESTIMATION SIMULTANEOUS LOCALIZATION AND MAPPING TRANSFER LEARNING
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.
MONOCULAR VISUAL ODOMETRY STEREO MATCHING STEREO MATCHING HAND
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.
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).
DEPTH AND CAMERA MOTION MONOCULAR VISUAL ODOMETRY MOTION ESTIMATION TRAJECTORY PREDICTION