# Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder

arXiv: https://arxiv.org/abs/2004.12811 · HTML: https://mlsanity.com/paper/2004.12811/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 16 of 16)

- [Variational AutoEncoder for Reference based Image Super-Resolution](https://mlsanity.com/paper/2106.04090/) (2021)
- [Multiple Style Transfer via Variational AutoEncoder](https://mlsanity.com/paper/2110.07375/) (2021)
- [Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations](https://mlsanity.com/paper/2104.03926/) (2021)
- [Deep Kernel Methods Learn Better: From Cards to Process Optimization](https://mlsanity.com/paper/2303.14554/) (2023)
- [Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets](https://mlsanity.com/paper/2308.10120/) (2023)
- [Deep Spatio-Temporal Neural Network for Air Quality Reanalysis](https://mlsanity.com/paper/2502.11941/) (2025)
- [From General to Specific: Online Updating for Blind Super-Resolution](https://mlsanity.com/paper/2107.02398/) (2021)
- [IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior](https://mlsanity.com/paper/2410.09111/) (2024)
- [See360: Novel Panoramic View Interpolation](https://mlsanity.com/paper/2401.03431/) (2024)
- [An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation](https://mlsanity.com/paper/2410.19063/) (2024)
- [Deep Variational Models for Collaborative Filtering-based Recommender Systems](https://mlsanity.com/paper/2107.12677/) (2021)
- [XVertNet: Unsupervised Contrast Enhancement of Vertebral Structures with Dynamic Self-Tuning Guidance and Multi-Stage Analysis](https://mlsanity.com/paper/2306.03983/) (2023)
- [Soft-IntroVAE for Continuous Latent space Image Super-Resolution](https://mlsanity.com/paper/2307.09008/) (2023)
- [Downscaling Neural Network for Coastal Simulations](https://mlsanity.com/paper/2408.16553/) (2024)
- [UnCapsTSR: An Unsupervised Transformer-based Image Super-Resolution Approach for Capsule Endoscopy Images](https://mlsanity.com/paper/2609.02476/) (2026)
- [CEM-TUDASR: Computationally efficient multi-modality transformer based unsupervised domain adaptive super-resolution approach](https://mlsanity.com/paper/2609.11201/) (2026)

## Abstract (arXiv)

Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image with high fidelity or better perceptual quality. Due to the lack of ground truth images in real life, people prefer a photo-realistic image with low fidelity to a blurry image with high fidelity. In this paper, we revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution. Given that real images contain various noise and artifacts, we propose a joint image denoising and super-resolution model via Variational AutoEncoder. We come up with a conditional variational autoencoder to encode the reference for dense feature vector which can then be transferred to the decoder for target image denoising. With the aid of the discriminator, an additional overhead of super-resolution subnetwork is attached to super-resolve the denoised image with photo-realistic visual quality. We participated the NTIRE2020 Real Image Super-Resolution Challenge. Experimental results show that by using the proposed approach, we can obtain enlarged images with clean and pleasant features compared to other supervised methods. We also compared our approach with state-of-the-art methods on various datasets to demonstrate the efficiency of our proposed unsupervised super-resolution model.