Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data.
Bin ChengInderjot Singh SagguRaunak ShahGaurav BansalDinesh BharadiaPublished in: CoRR (2020)
Keyphrases
- synthetic data
- depth estimation
- monocular images
- dynamic scenes
- depth cues
- stereo vision
- depth map
- depth perception
- stereo matching
- depth estimates
- depth information
- video sequences
- scene understanding
- stereo pair
- real world
- image sequences
- multi view
- data sets
- space time
- real image data
- video surveillance
- real scenes
- video frames
- pose estimation
- super resolution
- moving camera
- vision system
- stereo images
- motion segmentation
- specular reflection
- moving objects
- medical images
- high quality
- d scene