One scalar is all you need - absolute depth estimation using monocular self-supervision.
Alexandra DanaNadav CarmelAmit ShomerOfer ManelaTomer PelegPublished in: CoRR (2023)
Keyphrases
- depth estimation
- monocular images
- depth cues
- stereo vision
- depth map
- depth perception
- stereo matching
- depth estimates
- depth information
- dynamic scenes
- real scenes
- stereo pair
- scene understanding
- super resolution
- active learning
- model based pose estimation
- multi view
- image sequences
- feature matching
- real time
- three dimensional
- ego motion
- pose estimation
- vision system
- disparity map
- input data
- dynamic programming
- viewpoint
- feature points
- object recognition
- face recognition
- stereo images
- depth from defocus
- motion segmentation
- space time