Login / Signup

Self-Supervised Learning of Depth and Ego-Motion From Videos by Alternative Training and Geometric Constraints from 3-D to 2-D.

Jiaojiao FangGuizhong Liu
Published in: IEEE Trans. Cogn. Dev. Syst. (2023)
Keyphrases
  • geometric constraints
  • ego motion
  • video sequences
  • camera calibration
  • epipolar geometry
  • image analysis
  • machine learning
  • multiscale
  • object recognition
  • active learning
  • closed form
  • field of view
  • dynamic scenes