# CEM-TUDASR: Computationally efficient multi-modality transformer based unsupervised domain adaptive super-resolution approach

arXiv: https://arxiv.org/abs/2609.11201 · HTML: https://mlsanity.com/paper/2609.11201/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [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)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [Deep Learning for Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/1808.03344/) (2018)
- [Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network](https://mlsanity.com/paper/1803.01417/) (2018)
- [Unsupervised Learning for Real-World Super-Resolution](https://mlsanity.com/paper/1909.09629/) (2019)
- [ConvNets vs. Transformers: Whose Visual Representations are More Transferable?](https://mlsanity.com/paper/2108.05305/) (2021)
- [Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution](https://mlsanity.com/paper/2005.00953/) (2020)
- [Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder](https://mlsanity.com/paper/2004.12811/) (2020)
- [EndoL2H: Deep Super-Resolution for Capsule Endoscopy](https://mlsanity.com/paper/2002.05459/) (2020)
- [Unsupervised MRI Super-Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors](https://mlsanity.com/paper/2008.11921/) (2020)
- [Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention](https://mlsanity.com/paper/2003.08539/) (2020)
- [CT Super Resolution via Zero Shot Learning](https://mlsanity.com/paper/2012.08943/) (2020)
- [Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation](https://mlsanity.com/paper/2205.06891/) (2022)
- [An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal](https://mlsanity.com/paper/2302.02849/) (2023)

## Abstract (arXiv)

Wireless Capsule Endoscopy (WCE) enables non-invasive visualization of the gastrointestinal tract, but its miniaturized optics, sensor limitations, and wireless transmission constraints result in low-resolution images with reduced visibility of diagnostically important structures. This paper proposes CEM-TUDASR, a computationally efficient unsupervised Transformer-based super-resolution framework for WCE image enhancement without paired low-resolution (LR) and high-resolution (HR) training data. A domain-adaptive degradation network synthesizes realistic WCE-like LR images from HR conventional endoscopy images, reducing the domain gap and enabling effective unpaired learning. The SR generator integrates Deep Attention Blocks (DABs) and a Fusion Attention Block (FAB) to capture long-range contextual dependencies and fine local structures while preserving perceptual and structural fidelity. The model is trained on a curated dataset derived from Kvasir Capsule and evaluated on KID and GIANA for cross-dataset generalization. No-reference quality metrics, including BRISQUE, PIQE, NIQE, and the domain-specific EndoQM, show that CEM-TUDASR consistently outperforms existing unsupervised SR methods. Qualitative results further demonstrate improved restoration of mucosal textures, vascular patterns, and clinically relevant anatomical details. Cross-domain experiments on retinal images additionally demonstrate the adaptability of the framework. With only 2.67 million parameters and 169.94 GFLOPs, CEM-TUDASR achieves high-quality reconstruction while maintaining computational efficiency, making it suitable for resource-constrained clinical and embedded endoscopic applications.