MonoFormer: Towards Generalization of self-supervised monocular depth estimation with Transformers.
Jinwoo BaeSungho MoonSunghoon ImPublished in: CoRR (2022)
Keyphrases
- depth estimation
- monocular images
- depth cues
- depth map
- stereo vision
- depth perception
- stereo matching
- depth information
- scene understanding
- real scenes
- dynamic scenes
- depth estimates
- super resolution
- image sequences
- model based pose estimation
- feature matching
- stereo pair
- pose estimation
- vision system
- object detection
- viewpoint