Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-10

Blind Super-Resolution

3260 papers • 126 benchmarks • 313 datasets

Blind Super-Resolution is an image processing technique that aims to reconstruct high-resolution images from low-resolution counterparts without prior knowledge of the degradation process.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in blind-super-resolution-10

Trend

Dataset

Best Model

Actions

DIV2KRK - 4x upscaling

DIV2KRK - 4x upscaling

DIV2KRK - 2x upscaling

DIV2KRK - 2x upscaling

Libraries

i

Use these libraries to find blind-super-resolution-10 models and implementations

Datasets

BSD

Urban100

Set14

Set5

Manga109

BSD100

Subtasks

No subtasks available.

Most implemented papers

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

Chao Dong, Ying Shan, Liangbin Xie•Wed Jul 21 2021

This work extends the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data and employs a U-Net discriminator with spectral normalization to increase discriminator capability and stabilize the training dynamics.

1633

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Set5 - 2x upscaling

Set5 - 2x upscaling

Set5 - 4x upscaling

Set5 - 4x upscaling

Set14 - 2x upscaling

Set14 - 2x upscaling

BSD100 - 2x upscaling

BSD100 - 2x upscaling

Urban100 - 2x upscaling

Urban100 - 2x upscaling

Manga109 - 2x upscaling

Manga109 - 2x upscaling

Set14 - 4x upscaling

Set14 - 4x upscaling

BSD100 - 4x upscaling

BSD100 - 4x upscaling

Urban100 - 4x upscaling

Urban100 - 4x upscaling

Manga109 - 4x upscaling

Manga109 - 4x upscaling

Set5 - 3x upscaling

Set5 - 3x upscaling

Set14 - 3x upscaling

Set14 - 3x upscaling

BSD100 - 3x upscaling

BSD100 - 3x upscaling

Urban100 - 3x upscaling

Urban100 - 3x upscaling

Manga109 - 3x upscaling

Manga109 - 3x upscaling

DIV2KRK

DIV2KRK

KID-F

0

Blind Super-Resolution Kernel Estimation using an Internal-GAN

Sefi Bell-Kligler, Assaf Shocher, M. Irani•Thu Sep 05 2019

KernelGAN is introduced, an image-specific Internal-GAN, which trains solely on the LR test image at test time, and learns its internal distribution of patches, and leads to state-of-the-art results in Blind-SR when plugged into existing SR algorithms.

505 0

Blind Super-Resolution With Iterative Kernel Correction

W. Zuo, Chao Dong, Jinjin Gu, Hannan Lu•Fri Apr 05 2019

An iterative correction scheme -- IKC that achieves better results than direct kernel estimation in blind SR problem and an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD.

545 0

Exploiting Diffusion Prior for Real-World Image Super-Resolution

Chen Change Loy, Kelvin C. K. Chan, Shangchen Zhou, Jianyi Wang, Zongsheng Yue•Wed May 10 2023

A novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution by employing the time-aware encoder can achieve promising restoration results without altering the pre-trained synthesis model, thereby preserving the generative prior and minimizing training cost.

517 0

Blind image fusion for hyperspectral imaging with the directional total variation

C. Schönlieb, Leon Bungert, D. Coomes, Matthias Joachim Ehrhardt, Jennifer Rasch, Rafael Reisenhofer•Tue Oct 03 2017

Numerical results on real remote sensing data from plant sciences and urban monitoring show the potential of the proposed method and suggests that it is robust with respect to the regularization parameters, mis-registration and the shape of the kernel.

55 0

Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

S. Süsstrunk, Majed El Helou, Ruofan Zhou•Sun Mar 15 2020

This work presents an analysis, in the frequency domain, of degradation-kernel overfitting in super-resolution and introduces a conditional learning perspective that extends to both super- resolution and denoising and proposes a stochastic frequency masking of images used in training to regularize the networks and address the overfitting problem.

47 0

Deep Constrained Least Squares for Blind Image Super-Resolution

Shuaicheng Liu, Haibin Huang, Haoqiang Fan, Ziwei Luo, Lei Yu, Youwei Li•Mon Feb 14 2022

This paper reformulate the degradation model such that the deblurred kernel estimation can be transferred into the low resolution space and introduces a dynamic deep linear filter module that can adaptively generate deblurring kernel weights conditional on the input and yields more robust kernel estimation.

120 0

Unsupervised Degradation Representation Learning for Blind Super-Resolution

Yingqian Wang, Longguang Wang, Jungang Yang, W. An, Yulan Guo, Xiaoyu Dong, Qingyu Xu•Wed Mar 31 2021

This paper proposes an unsupervised degradation representation learning scheme for blind SR without explicit degradation estimation, and introduces a Degradation-Aware SR (DASR) network with flexible adaption to various degradations based on the learned representations.

375 0

Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors

Taojiannan Yang, Xiaoguang Han, Chaofeng Chen, Xiaoming Li, Xinyu Shi, Yipeng Qin, Shihui Guo•Fri Feb 25 2022

This work proposes Feature Matching SR (FeMaSR), which restores realistic HR images in a much more compact feature space by matching distorted LR image features to their distortion-free HR counterparts in the authors' pretrained HR priors, and decoding the matched features to obtain realisticHR images.

163 0

End-to-End Alternating Optimization for Real-World Blind Super Resolution

Tien-Ping Tan, Shang Li, Zhengxiong Luo, Yan Huang, Liangsheng Wang•Wed Aug 02 2023

This work designs two convolutional neural modules, namely Restorer and Estimator, which can estimate the degradation and restore the SR image in a single model and can largely outperform state-of-the-art methods and produce more visually favorable results.

30 0

Adding a benchmark result helps the community track progress.

Blind Super-Resolution | State-of-the-Art