OnionNet: Single-View Depth Prediction and Camera Pose Estimation for Unlabeled Video.
Tianhao GuZhe WangDongdong LiHai YangWenli DuYangming ZhouPublished in: IEEE Trans. Cogn. Dev. Syst. (2021)
Keyphrases
- single view
- camera pose estimation
- camera pose
- multi view
- depth map
- perspective projection
- scene reconstruction
- multiple views
- dynamic scenes
- view synthesis
- video sequences
- structure from motion
- surface reconstruction
- pose estimation
- depth information
- vanishing points
- d scene
- bundle adjustment
- active learning
- multiple cameras
- depth images
- viewpoint
- training set
- machine learning