Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume.
Adrian JohnstonGustavo CarneiroPublished in: CVPR (2020)
Keyphrases
- depth estimation
- monocular images
- stereo matching
- stereo pair
- disparity map
- depth cues
- stereo vision
- depth map
- stereo algorithms
- stereo images
- stereo camera
- binocular stereo
- stereo algorithm
- image sequences
- stereo correspondence
- depth information
- depth estimates
- real scenes
- belief propagation
- dynamic programming
- feature matching
- dynamic scenes
- disparity estimation
- super resolution
- image pairs
- depth discontinuities
- input image
- scene understanding
- ground truth
- multi camera
- pose estimation
- scene flow
- post processing
- multi view
- image matching
- high resolution
- high quality
- object boundaries
- three dimensional