GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network.
Armin MasoumianHatem A. RashwanSaddam AbdulwahabJulián CristianoDomenec PuigPublished in: CoRR (2021)
Keyphrases
- depth estimation
- depth map
- stereo vision
- convolutional network
- stereo matching
- convolutional neural networks
- depth information
- dynamic scenes
- image sequences
- graph matching
- scene understanding
- super resolution
- multi view
- pose estimation
- feature matching
- real scenes
- stereo pair
- d scene
- coarse to fine
- three dimensional
- image analysis
- stereo images
- image pairs
- high quality
- feature points
- object detection
- feature vectors
- computer vision