Multi-Frame Self-Supervised Depth with Transformers.
Vitor GuiziliniRares AmbrusDian ChenSergey ZakharovAdrien GaidonPublished in: CVPR (2022)
Keyphrases
- multi frame
- motion estimation
- point correspondences
- image sequences
- multiple frames
- optical flow
- super resolution
- temporal coherence
- depth map
- single frame
- motion analysis
- computationally efficient
- optic flow
- stereo correspondence
- video frames
- filtering algorithm
- super resolution image reconstruction
- low resolution
- image analysis
- multimedia