BriefGPT.xyz
Mar, 2018
基于稠密三维流的单目视觉里程计与稠密三维建图学习
Learning monocular visual odometry with dense 3D mapping from dense 3D flow
HTML
PDF
Cheng Zhao, Li Sun, Pulak Purkait, Tom Duckett, Rustam Stolkin
TL;DR
本文介绍了一个全新的深度学习方法来进行单目 SLAM，通过使用学习视觉里程计（L-VO）和稠密 3D 映射的神经网络，该方法能够实现同时定位与建图。
Abstract
This paper introduces a fully
deep learning
approach to monocular
slam
, which can perform simultaneous localization using a
neural network
→