Sign in
A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation.
Xiuyuan Li
Jiangang Yu
Fengchao Li
Guowen An
Published in:
CoRR (2022)
Keyphrases
</>
visual odometry
depth map
depth images
ego motion
stereo vision
image sequences
depth information
three dimensional
pose estimation
stereo matching
dynamic scenes
high quality
optical flow
generative model
range images
range data