# Alternative Learning Paradigms for Image Quality Transfer

arXiv: https://arxiv.org/abs/2411.05885 · HTML: https://mlsanity.com/paper/2411.05885/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 61 references that are in the map.
- First posted on arXiv 8 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations](https://mlsanity.com/paper/2004.06965/) (2020)
- [Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast](https://mlsanity.com/paper/2012.13340/) (2020)
- [Group-based Sparse Representation for Image Restoration](https://mlsanity.com/paper/1405.3351/) (2014)
- [Low-field magnetic resonance image enhancement via stochastic image quality transfer](https://mlsanity.com/paper/2304.13385/) (2023)
- [Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks](https://mlsanity.com/paper/2004.06163/) (2020)
- [Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness](https://mlsanity.com/paper/2105.07139/) (2021)
- [A 3D Conditional Diffusion Model for Image Quality Transfer -- An Application to Low-Field MRI](https://mlsanity.com/paper/2311.06631/) (2023)
- [When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data](https://mlsanity.com/paper/2005.10940/) (2020)
- [Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images](https://mlsanity.com/paper/1808.05577/) (2018)
- [Deep Learning for Low-Field to High-Field MR: Image Quality Transfer with Probabilistic Decimation Simulator](https://mlsanity.com/paper/1909.06763/) (2019)
- [Patch-Based Sparse Representation For Bacterial Detection](https://mlsanity.com/paper/1810.12043/) (2018)
- [Deep Sparse Coding for Non-Intrusive Load Monitoring](https://mlsanity.com/paper/1912.12128/) (2019)
- [Deep Bi-directional Attention Network for Image Super-Resolution Quality Assessment](https://mlsanity.com/paper/2403.10406/) (2024)

## Built on by (most cited first, 4 of 4)

- [Low-Field Magnetic Resonance Image Quality Enhancement using a Conditional Flow Matching Model](https://mlsanity.com/paper/2510.12408/) (2025)
- [Direct low-field MRI super-resolution using undersampled k-space](https://mlsanity.com/paper/2603.00668/) (2026)
- [Low-Field Magnetic Resonance Image Quality Enhancement using Undersampled k-Space and Out-of-Distribution Generalisation](https://mlsanity.com/paper/2603.14120/) (2026)
- [Low-Field Magnetic Resonance Image Enhancement using Undersampled k-Space](https://mlsanity.com/paper/2603.14125/) (2026)

## Abstract (arXiv)

Image Quality Transfer (IQT) aims to enhance the contrast and resolution of low-quality medical images, e.g. obtained from low-power devices, with rich information learned from higher quality images. In contrast to existing IQT methods which adopt supervised learning frameworks, in this work, we propose two novel formulations of the IQT problem. The first approach uses an unsupervised learning framework, whereas the second is a combination of both supervised and unsupervised learning. The unsupervised learning approach considers a sparse representation (SRep) and dictionary learning model, which we call IQT-SRep, whereas the combination of supervised and unsupervised learning approach is based on deep dictionary learning (DDL), which we call IQT-DDL. The IQT-SRep approach trains two dictionaries using a SRep model using pairs of low- and high-quality volumes. Subsequently, the SRep of a low-quality block, in terms of the low-quality dictionary, can be directly used to recover the corresponding high-quality block using the high-quality dictionary. On the other hand, the IQT-DDL approach explicitly learns a high-resolution dictionary to upscale the input volume, while the entire network, including high dictionary generator, is simultaneously optimised to take full advantage of deep learning methods. The two models are evaluated using a low-field magnetic resonance imaging (MRI) application aiming to recover high-quality images akin to those obtained from high-field scanners. Experiments comparing the proposed approaches against state-of-the-art supervised deep learning IQT method (IQT-DL) identify that the two novel formulations of the IQT problem can avoid bias associated with supervised methods when tested using out-of-distribution data that differs from the distribution of the data the model was trained on. This highlights the potential benefit of these novel paradigms for IQT.