Temporal-Aware SfM-Learner: Unsupervised Learning Monocular Depth and Motion from Stereo Video Clips.
Lanqing ZhangGe LiThomas H. LiPublished in: MIPR (2020)
Keyphrases
- video clips
- depth cues
- unsupervised learning
- depth perception
- depth estimates
- structure from motion
- image sequences
- depth information
- depth map
- temporal information
- temporal order
- camera motion
- stereo vision
- ego motion
- video database
- depth estimation
- video frames
- stereo camera
- video data
- spatial and temporal
- optical flow
- motion estimates
- key frames
- relative depth
- spatio temporal
- video sequences
- stereo disparity
- video retrieval
- video streams
- space time
- motion analysis
- motion trajectories
- visual odometry
- video content
- bundle adjustment
- e learning
- motion estimation
- video shots
- semi supervised
- three dimensional
- moving objects
- computer vision
- dynamic textures
- motion parameters
- multi view
- human motion
- motion model
- d scene
- stereo pair
- active learning
- image classification
- focal length
- disparity map
- spatial information