CATNet: Convolutional attention and transformer for monocular depth estimation.
Shuai TangTongwei LuXuanxuan LiuHuabing ZhouYanduo ZhangPublished in: Pattern Recognit. (2024)
Keyphrases
- depth estimation
- monocular images
- depth cues
- depth map
- stereo vision
- stereo matching
- depth perception
- depth estimates
- depth information
- image sequences
- dynamic scenes
- super resolution
- real scenes
- scene understanding
- model based pose estimation
- stereo pair
- feature matching
- disparity map
- stereo images
- multi view
- pose estimation
- high quality
- d scene
- specular reflection
- spatio temporal
- three dimensional
- surface reconstruction
- image processing
- belief propagation
- d objects
- dynamic programming