Adaptable 2D to 3D Stereo Vision Image Conversion Based on a Deep Convolutional Neural Network and Fast Inpaint Algorithm.
Tomasz HachajPublished in: Entropy (2023)
Keyphrases
- stereo vision
- disparity map
- dynamic programming
- learning algorithm
- preprocessing
- image features
- block matching algorithm
- stereo matching algorithm
- stereo algorithm
- reconstruction method
- color constancy
- stereo matching
- convolutional neural network
- depth estimation
- image matching
- detection algorithm
- single image
- image analysis
- post processing
- detection method
- vision system
- input data
- motion estimation
- ground truth
- image data
- high resolution
- pairwise
- feature space
- multiscale
- machine learning