An Epipolar Volume Autoencoder With Adversarial Loss for Deep Light Field Super-Resolution.
Minchen ZhuAnna AlperovichOle JohannsenAntonin SulcBastian GoldlueckePublished in: CVPR Workshops (2019)
Keyphrases
- light field
- super resolution
- low resolution
- high resolution
- image reconstruction
- image restoration
- low resolution images
- image based rendering
- high quality
- single image
- motion blur
- motion estimation
- image super resolution
- epipolar geometry
- super resolution reconstruction
- high resolution images
- image formation
- multi frame
- imaging process
- multi view
- scene geometry
- super resolution algorithm
- machine learning
- blurred images
- image pairs
- remote sensing
- image registration
- viewpoint
- super resolved