Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos.
Haofei XuJianmin ZhengJianfei CaiJuyong ZhangPublished in: CoRR (2019)
Keyphrases
- depth estimation
- monocular images
- dynamic scenes
- depth cues
- depth map
- stereo vision
- stereo matching
- depth information
- image sequences
- scene understanding
- depth estimates
- input image
- real scenes
- space time
- stereo pair
- video sequences
- pose estimation
- video surveillance
- super resolution
- disparity map
- object recognition
- video data
- feature matching
- optical flow
- high quality