
TL;DR
This paper introduces a novel patch-based learning framework that enables effective image restoration using only a single image, significantly reducing data requirements and improving generalization for tasks like deblurring and super-resolution.
Contribution
The work presents a minimal-data supervised learning approach that trains on just one image or part of an image, enhancing efficiency and robustness in image restoration tasks.
Findings
Effective image deblurring and super-resolution with one image
Improved sample efficiency and generalization
Reduced computational complexity
Abstract
Image restoration, or inverse problems in image processing, has long been an extensively studied topic. In recent years supervised learning approaches have become a popular strategy attempting to tackle this task. Unfortunately, most supervised learning-based methods are highly demanding in terms of 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, we try to answer a fundamental question: Can supervised learning models generalize well solely by learning from one image or even part of an image? If so, then what is the minimal amount of patches required to achieve acceptable generalization? To this end, we focus on an efficient patch-based learning framework that requires a single image input-output pair for training.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMedical Imaging Techniques and Applications · Advanced X-ray and CT Imaging · Photoacoustic and Ultrasonic Imaging
MethodsFocus
