Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation.
Ning ZhangFrancesco NexGeorge VosselmanNorman KerlePublished in: CVPR (2023)
Keyphrases
- lightweight
- depth estimation
- monocular images
- stereo vision
- depth map
- depth cues
- stereo matching
- communication infrastructure
- depth perception
- image sequences
- depth estimates
- depth information
- disparity map
- scene understanding
- pose estimation
- real scenes
- dynamic scenes
- model based pose estimation
- stereo pair
- wireless sensor networks
- image processing
- real time
- feature matching
- image pairs
- camera motion
- color images
- high resolution