GCNDepth: Self-supervised monocular depth estimation based on graph convolutional network.
Armin MasoumianHatem A. RashwanSaddam AbdulwahabJulián CristianoM. Salman AsifDomenec PuigPublished in: Neurocomputing (2023)
Keyphrases
- depth estimation
- stereo vision
- depth map
- convolutional network
- stereo matching
- depth information
- convolutional neural networks
- image sequences
- dynamic scenes
- scene understanding
- real scenes
- stereo pair
- high quality
- super resolution
- object boundaries
- multi class
- disparity map
- pose estimation
- deformable models
- multiple views
- d scene
- three dimensional
- pairwise