Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions.
Zeyuan Allen-ZhuYuanzhi LiPublished in: CoRR (2021)
Keyphrases
- super resolution
- generative model
- low resolution
- high resolution
- image reconstruction
- probabilistic model
- mixture model
- low resolution images
- discriminative models
- high quality
- discriminative learning
- prior knowledge
- bayesian framework
- motion estimation
- image processing
- probability distribution
- semi supervised
- em algorithm
- graphical models
- depth map
- random variables
- expectation maximization
- image patches
- latent variables
- object categories
- object recognition
- face recognition
- data sets