Real Image Super-Resolution using GAN through modeling of LR and HR process
Not on the map. Why?
Abstract (arXiv)
The current existing deep image super-resolution methods usually assume that a Low Resolution (LR) image is bicubicly downscaled of a High Resolution (HR) image. However, such an ideal bicubic downsampling process is different from the real LR degradations, which usually come from complicated combinations of different degradation processes, such as camera blur, sensor noise, sharpening artifacts, JPEG compression, and further image editing, and several times image transmission over the internet and unpredictable noises. It leads to the highly ill-posed nature of the inverse upscaling problem. To address these issues, we propose a GAN-based SR approach with learnable adaptive sinusoidal nonlinearities incorporated in LR and SR models by directly learn degradation distributions and then synthesize paired LR/HR training data to train the generalized SR model to real image degradations. We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 19 Oct 2022.
Builds on
29 of 38 references.
References · 29
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
- 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
- 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
- 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
- 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
17 more
- 2019Feedback Network for Image Super-Resolutioncited by 155
- 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
- 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
- 2019Frequency Separation for Real-World Super-Resolutioncited by 115
- 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
- 2020Cross-Scale Internal Graph Neural Network for Image Super-Resolutioncited by 94
- 2021LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyondcited by 88
- 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
- 2020Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategycited by 66
- 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
- 2015Seven ways to improve example-based single image super resolutioncited by 51
- 2018A representer theorem for deep neural networkscited by 38
- 2020Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolutioncited by 17
- 2020Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolutioncited by 7
- 2019Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradationscited by 4
- 2020Deep Iterative Residual Convolutional Network for Single Image Super-Resolutioncited by 4
- 2021A Deep Residual Star Generative Adversarial Network for multi-domain Image Super-Resolutioncited by 2
Built on by
Not cited yet.