3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose From Monocular Video.
Guangming WangJiquan ZhongShijie ZhaoWenhua WuZhe LiuHesheng WangPublished in: IEEE Trans. Circuits Syst. Video Technol. (2023)
Keyphrases
- unsupervised learning
- pose estimation
- pose tracking
- depth cues
- video data
- pose recovery
- monocular images
- depth perception
- depth video
- image sequences
- video sequences
- multimedia
- supervised learning
- depth images
- video content
- semi supervised
- person detection
- position and orientation
- d objects
- human pose
- depth map
- video frames
- video streams
- model selection
- depth information
- deep learning
- machine learning
- depth image based rendering
- object recognition
- dimensionality reduction
- calibrated cameras
- ego motion
- depth estimation
- expectation maximization
- dynamic scenes
- visual cues
- feature selection
- deep architectures
- real time
- key frames