CVPR2020
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Sachit Menon, Alexandru Damian, Shijia Hu, Nikhil Ravi, Cynthia Rudin
Abstract
- It accomplishes this in an entirely self-supervised fashion. 2. It is not confined to a specific degradation operator used during training. 3. This is formalized through the "down-scaling loss," which guides exploration through the latent space of a generative model. PULSE thereby generates super-resolved images that both are realistic and downscale correctly.