MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer.
Chaoqiang ZhaoYoumin ZhangMatteo PoggiFabio TosiXianda GuoZheng ZhuGuan HuangYang TangStefano MattocciaPublished in: CoRR (2022)
Keyphrases
- depth estimation
- monocular images
- depth cues
- stereo vision
- depth map
- binocular vision
- binocular stereo
- depth perception
- vision system
- stereo matching
- depth information
- scene understanding
- depth estimates
- dynamic scenes
- real scenes
- image sequences
- stereo pair
- computer vision
- super resolution
- feature matching
- disparity map
- model based pose estimation
- pose estimation
- high quality
- stereo images
- d scene
- three dimensional
- object tracking
- low resolution
- markov random field
- depth from defocus
- viewpoint
- real time