Restore image by learning from one image using efficient patch-based learning with Pereg
Restore image by learning from one image using efficient patch-based learning with Pereg
One-Shot Image Restoration
arXiv paper abstract https://arxiv.org/abs/2404.17426
arXiv PDF paper https://arxiv.org/pdf/2404.17426
Image restoration, or inverse problems in image processing, has long been an extensively studied topic.
… supervised learning … popular … to tackle this task. Unfortunately, … demanding in … computational resources and training data (sample complexity).
In addition, trained models are sensitive to domain changes, such as varying acquisition systems, signal sampling rates, resolution and contrast.
In this work, … try to answer … Can supervised learning … learning from one image … what is the minimal amount of patches required … focus on an efficient patch-based learning framework that requires a single image input-output pair for training.
Experimental results demonstrate the applicability, robustness and computational efficiency of the proposed approach for supervised image deblurring and super-resolution.
… significant improvement of learning models’ sample efficiency, generalization and time complexity … for future real-time applications, and applied to other signals and modalities.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
