SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks.

Tuo Feng Dongbing Gu

Published in: CoRR (2019)

Keyphrases

depth estimation
visual odometry
stereo vision
depth map
depth images
depth information
stereo matching
scene understanding
real scenes
stereo pair
ego motion
generative model
vision system
dynamic scenes
real time
object recognition
super resolution
feature matching
semi supervised
viewpoint