Depth map upsampling using joint edge-guided convolutional neural network for virtual view synthesizing.
Yan DongChunyu LinYao ZhaoChao YaoPublished in: J. Electronic Imaging (2017)
Keyphrases
- depth map
- convolutional neural network
- virtual view
- view synthesis
- free viewpoint
- multi view
- face detection
- depth information
- three dimensional
- free viewpoint video
- high quality
- d scene
- stereo matching
- input image
- virtual view synthesis
- object boundaries
- real scenes
- high resolution
- image sequences
- depth images
- low resolution
- depth estimation
- super resolution
- stereo pair
- image based rendering
- multiple views
- object detection
- view dependent
- pairwise
- optical flow
- computer vision
- machine learning