Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos.
Haofei XuJianmin ZhengJianfei CaiJuyong ZhangPublished in: IJCAI (2019)
Keyphrases
- depth estimation
- monocular images
- dynamic scenes
- depth map
- depth cues
- stereo vision
- stereo matching
- depth information
- image sequences
- real scenes
- video sequences
- input image
- super resolution
- scene understanding
- multi view
- pose estimation
- stereo pair
- video frames
- depth estimates
- moving camera
- d scene
- specular reflection
- semi supervised
- video surveillance
- video data
- low resolution
- face images
- image registration
- optical flow
- feature vectors
- high quality
- face recognition