METER: a mobile vision transformer architecture for monocular depth estimation.
Lorenzo PapaP. RussoIrene AmeriniPublished in: CoRR (2024)
Keyphrases
- depth estimation
- monocular images
- stereo vision
- depth cues
- depth map
- binocular stereo
- depth perception
- binocular vision
- stereo matching
- vision system
- depth information
- dynamic scenes
- real time
- image sequences
- scene understanding
- computer vision
- super resolution
- depth estimates
- model based pose estimation
- multi view
- feature matching
- real scenes
- high quality
- image processing
- belief propagation
- pose estimation
- low resolution
- motion estimation
- high resolution