Methods › Computer Vision › Generative Adversarial Networks › SRGAN
SRGAN
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SRGAN is a generative adversarial network for single image super-resolution. It uses a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes the solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, the authors use a content loss motivated by perceptual similarity instead of similarity in pixel space. The actual networks - depicted in the Figure to the right - consist mainly of residual blocks for feature extraction.
Formally we write the perceptual loss function as a weighted sum of a (VGG) content loss l^(SR)_X and an adversarial loss component l^(SR)_(Gen):
l^(SR) = l^(SR)_X + 10⁻³l^(SR)_(Gen)
Papers archive 2025-07-28
29 shown of 29, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Super-Resolution Generative Adversarial Networks based Video Enhancement 14 May 2025 · 0 repositories · arXiv:2505.10589
-
Uncertainty Estimation for Super-Resolution using ESRGAN 19 Dec 2024 · 0 repositories · arXiv:2412.15439
-
Deep Learning-Based CKM Construction with Image Super-Resolution 28 Oct 2024 · 1 repository · arXiv:2411.08887
-
Power-Efficient Image Storage: Leveraging Super Resolution Generative Adversarial Network for Sustainable Compression and Reduced Carbon Footprint 6 Apr 2024 · 0 repositories · arXiv:2404.04642
-
Fully Data-Driven Model for Increasing Sampling Rate Frequency of Seismic Data using Super-Resolution Generative Adversarial Networks 31 Jan 2024 · 0 repositories · arXiv:2402.00153
-
Texture and Noise Dual Adaptation for Infrared Image Super-Resolution 15 Nov 2023 · 1 repository · arXiv:2311.08816
-
Guided Frequency Loss for Image Restoration 27 Sep 2023 · 0 repositories · arXiv:2309.15563
-
More Reliable AI Solution: Breast Ultrasound Diagnosis Using Multi-AI Combination 7 Jan 2021 · 0 repositories · arXiv:2101.02639
-
Super-resolution Guided Pore Detection for Fingerprint Recognition 10 Dec 2020 · 0 repositories · arXiv:2012.05959
-
Fully Quantized Image Super-Resolution Networks 29 Nov 2020 · 1 repository · arXiv:2011.14265
-
Micro CT Image-Assisted Cross Modality Super-Resolution of Clinical CT Images Utilizing Synthesized Training Dataset 20 Oct 2020 · 0 repositories · arXiv:2010.10207
-
Attaining Real-Time Super-Resolution for Microscopic Images Using GAN 9 Oct 2020 · 1 repository · arXiv:2010.04634
-
Increasing the Sentinel-2 potential for marine plastic litter monitoring through image fusion techniques 30 Jul 2020 · 1 repository
-
Journey Towards Tiny Perceptual Super-Resolution 8 Jul 2020 · 2 repositories · arXiv:2007.04356
-
Perceptual Extreme Super Resolution Network with Receptive Field Block 26 May 2020 · 1 repository · arXiv:2005.12597Syntology ran 0 of 3 samples · 3 unverified
-
Arbitrary Scale Super-Resolution for Brain MRI Images 5 Apr 2020 · 1 repository · arXiv:2004.02086
-
EndoL2H: Deep Super-Resolution for Capsule Endoscopy 13 Feb 2020 · 3 repositories · arXiv:2002.05459
-
An Application of Generative Adversarial Networks for Super Resolution Medical Imaging 19 Dec 2019 · 0 repositories · arXiv:1912.09507
-
Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks 19 Dec 2019 · 0 repositories · arXiv:1912.09497
-
Image Super-Resolution Using a Wavelet-based Generative Adversarial Network 24 Jul 2019 · 1 repository · arXiv:1907.10213
-
Boosting Resolution and Recovering Texture of micro-CT Images with Deep Learning 15 Jul 2019 · 0 repositories · arXiv:1907.07131
-
SRGAN: Training Dataset Matters 24 Mar 2019 · 1 repository · arXiv:1903.09922
-
SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network 18 Dec 2018 · 0 repositories · arXiv:1812.07174
-
Bi-GANs-ST for Perceptual Image Super-resolution 1 Nov 2018 · 0 repositories · arXiv:1811.00367
-
Super-Resolution via Conditional Implicit Maximum Likelihood Estimation 2 Oct 2018 · 0 repositories · arXiv:1810.01406
-
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks 1 Sep 2018 · 46 repositories · arXiv:1809.00219Syntology ran 8 of 44 samples · 36 unverified
-
Wide Activation for Efficient and Accurate Image Super-Resolution 27 Aug 2018 · 12 repositories · arXiv:1808.08718Syntology ran 0 of 17 samples · 17 unverified · 2 pointer-only (licence)
-
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform 9 Apr 2018 · 4 repositories · arXiv:1804.02815
-
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network 15 Sep 2016 · 140 repositories · arXiv:1609.04802Syntology ran 16 of 72 samples · 56 unverified · 11 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 31 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Super-Resolution | 27 |
| Image Super-Resolution | 19 |
| Generative Adversarial Network | 9 |
| SSIM | 7 |
| Video Super-Resolution | 2 |
| Brain Tumor Segmentation | 1 |
| Data Compression | 1 |
| Deep Learning | 1 |
| Denoising | 1 |
| Domain Adaptation | 1 |
| Edge Detection | 1 |
| Face Hallucination | 1 |
| GPU | 1 |
| Image Compression | 1 |
| Image Enhancement | 1 |
| Image Generation | 1 |
| Image Restoration | 1 |
| Infrared image super-resolution | 1 |
| Medical Diagnosis | 1 |
| Meta-Learning | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections