Self-Supervised Learning for Image Super-Resolution and Deblurring

• URL: http://arxiv.org/abs/2312.11232v2
• Date: Tue, 19 Mar 2024 17:05:57 GMT
• Title: Self-Supervised Learning for Image Super-Resolution and Deblurring
• Authors: Jérémy Scanvic, Mike Davies, Patrice Abry, Julián Tachella,
• Abstract summary: Self-supervised methods have recently proved to be nearly as effective as supervised methods in various imaging inverse problems. We propose a new self-supervised approach that leverages the fact that many image distributions are approximately scale-invariant. We demonstrate throughout a series of experiments on real datasets that the proposed method outperforms other self-supervised approaches.
• Score: 9.587978273085296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised methods have recently proved to be nearly as effective as supervised methods in various imaging inverse problems, paving the way for learning-based methods in scientific and medical imaging applications where ground truth data is hard or expensive to obtain. This is the case in magnetic resonance imaging and computed tomography. These methods critically rely on invariance to translations and/or rotations of the image distribution to learn from incomplete measurement data alone. However, existing approaches fail to obtain competitive performances in the problems of image super-resolution and deblurring, which play a key role in most imaging systems. In this work, we show that invariance to translations and rotations is insufficient to learn from measurements that only contain low-frequency information. Instead, we propose a new self-supervised approach that leverages the fact that many image distributions are approximately scale-invariant, and that enables recovering high-frequency information lost in the measurement process. We demonstrate throughout a series of experiments on real datasets that the proposed method outperforms other self-supervised approaches, and obtains performances on par with fully supervised learning.

Related papers

• Private, Efficient and Scalable Kernel Learning for Medical Image Analysis [1.7999333451993955]
  OKRA (Orthonormal K-fRAmes) is a novel randomized encoding-based approach for kernel-based machine learning. It significantly enhances scalability and speed compared to current state-of-the-art solutions.
  arXiv  Detail & Related papers  (2024-10-21T10:03:03Z)
• Learning from Multi-Perception Features for Real-Word Image Super-resolution [87.71135803794519]
  We propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information. We also introduce a contrastive regularization term (CR) that improves the model's learning capability.
  arXiv  Detail & Related papers  (2023-05-26T07:35:49Z)
• Single-photon Image Super-resolution via Self-supervised Learning [6.218646347012887]
  Single-Photon Image Super-Resolution (SPISR) aims to recover a high-resolution photon counting cube from a noisy low-resolution one by computational imaging algorithms. By extending Equivariant Imaging (EI) to single-photon data, we propose a self-supervised learning framework for the SPISR task.
  arXiv  Detail & Related papers  (2023-03-03T15:52:01Z)
• Real-World Image Super-Resolution by Exclusionary Dual-Learning [98.36096041099906]
  Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input. Deep learning-based methods have achieved promising restoration quality on real-world image super-resolution datasets. We propose Real-World image Super-Resolution by Exclusionary Dual-Learning (RWSR-EDL) to address the feature diversity in perceptual- and L1-based cooperative learning.
  arXiv  Detail & Related papers  (2022-06-06T13:28:15Z)
• Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problems [10.115302976900445]
  Tomographic imaging is in general an ill-posed inverse problem. We propose a new empirical sampling method that computes multiple solutions of a tomographic inverse problem.
  arXiv  Detail & Related papers  (2022-02-10T20:27:31Z)
• Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images [79.34600869202373]
  We show that inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transferable representations among seen and unseen classes. Specifically, we propose a novel part-based self-supervised representation learning scheme to learn transferable representations. Our method yields impressive results, outperforming the previous best unsupervised methods by 7.74% and 9.24%.
  arXiv  Detail & Related papers  (2021-05-25T12:22:11Z)
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection [66.10057490293981]
  We propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection. Our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin.
  arXiv  Detail & Related papers  (2021-03-29T09:27:23Z)
• Improving Blind Spot Denoising for Microscopy [73.94017852757413]
  We present a novel way to improve the quality of self-supervised denoising. We assume the clean image to be the result of a convolution with a point spread function (PSF) and explicitly include this operation at the end of our neural network.
  arXiv  Detail & Related papers  (2020-08-19T13:06:24Z)
• Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations [68.8204255655161]
  Anomaly detection for Magnetic Resonance Images (MRIs) can be solved with unsupervised methods. We have proposed a slice-wise semi-supervised method for tumour detection based on the computation of a dissimilarity function in the latent space of a Variational AutoEncoder. We show that by training the models on higher resolution images and by improving the quality of the reconstructions, we obtain results which are comparable with different baselines.
  arXiv  Detail & Related papers  (2020-07-24T14:02:09Z)
• Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation [18.870983535180457]
  We propose Transformation Consistency Regularization, which delves into a more challenging setting of image-to-image translation. We evaluate the efficacy of our algorithm on three different applications: image colorization, denoising and super-resolution. Our method is significantly data efficient, requiring only around 10 - 20% of labeled samples to achieve similar image reconstructions to its fully-supervised counterpart.
  arXiv  Detail & Related papers  (2020-07-15T17:41:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.