MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer.
Chaoqiang ZhaoYoumin ZhangMatteo PoggiFabio TosiXianda GuoZheng ZhuGuan HuangYang TangStefano MattocciaPublished in: 3DV (2022)
Keyphrases
- depth estimation
- monocular images
- depth cues
- stereo vision
- depth map
- depth perception
- binocular vision
- binocular stereo
- vision system
- stereo matching
- depth information
- scene understanding
- dynamic scenes
- depth estimates
- real scenes
- computer vision
- super resolution
- model based pose estimation
- stereo pair
- image sequences
- disparity map
- multi view
- feature matching
- stereo images
- pose estimation
- depth from defocus
- three dimensional
- image processing
- real time
- object recognition