vo网络汇总

FLOWNET

FlowNet .png FlowNet 2.0.png

监督
DeepVO

DeepVO.png

Deep Auxiliary Learning for Visual Localization and Odometry

Deep Auxiliary Learning for Visual Localization and Odometry.png
Deep Global-Relative Networks for End-to-End 6-DoF VisualLocalization and Odometry Deep Global-Relative Networks for End-to-End 6-DoF VisualLocalization and Odometry.png
Guided Feature Selection for Deep VisualOdometry.png Learning monocular visual odometry with dense 3D mappingfrom dense 3D flow.png SfMLearner++: Learning Monocular Depth & Ego-Motion using MeaningfulGeometric Constraints.png VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry.png

半监督

Geometric Consistency for Self-Supervised End-to-End Visual Odometry.png Self-Improving Visual Odometry.png

非监督

GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks.png GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose.png UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning.png Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction.png Unsupervised Learning of Multi-Frame Optical Flow with Occlusions.png

辅助

CNN-SVO: Improving the Mapping in Semi-Direct Visual OdometryUsing Single-Image Depth Prediction.png

VSO