GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation.
Zezheng ZhangRyan K. Y. ChanKenneth K. Y. WongPublished in: CoRR (2023)
Keyphrases
- depth estimation
- monocular images
- depth cues
- depth map
- stereo vision
- depth information
- depth perception
- stereo matching
- depth estimates
- stereo camera
- image sequences
- dynamic scenes
- scene understanding
- dense depth maps
- real scenes
- multi view
- super resolution
- stereo pair
- feature matching
- disparity map
- d scene
- input image
- real time
- stereo images
- motion parallax
- three dimensional
- specular reflection
- pose estimation
- vision system
- depth from defocus
- high quality
- ego motion