Improve resolution of image when noise unknown by training with artificial data
Improve resolution of image when noise unknown by training with artificial data
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
arXiv paper abstract https://arxiv.org/abs/2107.10833
arXiv PDF paper https://arxiv.org/pdf/2107.10833.pdf
Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images.
... extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.
... better simulate complex real-world degradations.
... consider the common ringing and overshoot artifacts in the synthesis process.
... superior visual performance than prior works on various real datasets. We also provide efficient implementations to synthesize training pairs on the fly.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments