Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Non-Premixed Combustion on Non-Uniform Meshes and Demonstration of an Accelerated Simulation Workflow.
Mathis BodePublished in: CoRR (2022)
Keyphrases
- unsupervised learning
- super resolution
- low resolution
- high resolution
- image reconstruction
- image restoration
- low resolution images
- high resolution images
- resolution enhancement
- motion blur
- super resolved
- motion estimation
- video super resolution
- multiresolution
- single image super resolution
- image super resolution
- single frame
- high quality
- super resolution reconstruction
- multi frame
- image resolution
- depth map
- image patches
- computational complexity
- adaptive regularization
- three dimensional
- higher resolution
- d mesh
- computer vision
- light field
- degraded images
- image formation
- spatial resolution
- generative model
- multi view
- d objects
- super resolution image reconstruction