Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution.
Baoli SunXinchen YeBaopu LiHaojie LiZhihui WangRui XuPublished in: CVPR (2021)
Keyphrases
- knowledge transfer
- super resolution
- low resolution
- high resolution
- depth map
- transfer learning
- learning algorithm
- knowledge sharing
- image reconstruction
- scene structure
- learning tasks
- motion estimation
- active learning
- high quality
- supervised learning
- prior knowledge
- multi frame
- labeled data
- d scene
- optical flow
- computational complexity
- computer vision