A Review of Benchmark Datasets and Training Loss Functions in Neural Depth Estimation.
Faisal KhanShahid HussainShubhajit BasakMohamed MoustafaPeter CorcoranPublished in: IEEE Access (2021)
Keyphrases
- benchmark datasets
- loss function
- depth estimation
- depth map
- stereo vision
- pairwise
- stereo matching
- support vector
- learning to rank
- stereo pair
- depth information
- ranking models
- dynamic scenes
- training set
- real scenes
- ensemble methods
- scene understanding
- feature matching
- object recognition
- multi view
- supervised learning
- training data
- object detection
- multi class
- feature space
- similarity measure