GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and egomotion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in an end-to-end manner. Specifically, geometric relationships ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Yin, Zhichao, Shi, Jianping
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Geometry
Image reconstruction
Optical imaging
Task analysis
Three-dimensional displays
Unsupervised learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!