Super Resolution Benchmarks

本数据集来自于AIM 2022 压缩图像和视频超分辨率挑战赛”中的前 5 名解决方案工作：Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration

We are not the owners of this data. We compiled the most famous benchmarks for:

1. image super-resolution (SR)


2. image denoising


3. jpeg compression artifacts removal

Classical image super-resolution (SR)
DIV2K validation + Set5 + Set14 + BSD100 + Urban100 + Manga109 - download here

real-world image SR
RealSRSet and 5images- download here

grayscale/color JPEG compression artifact reduction
Classic5 +LIVE1 - download here

Kaggle is the world’s largest data science community with powerful tools and resources to help you achieve your data science goals.

Super resolution is the task of taking an input of a low resolution (LR) and upscaling it to that of a high resolution.

You can find relevant leaderboards in the subtasks below.

( Credit: [MemNet]( MemNet) )

Super resolution is the task of taking an input of a low resolution (LR) and upscaling it to that of a high resolution.

You can find relevant leaderboards in the subtasks below.

( Credit: [MemNet]( MemNet) )

AMD FidelityFX™ Super Resolution (FSR) uses cutting-edge upscaling technology to boost framerates & deliver near-native resolution with high-quality detail.

Tom's Hardware helps you buy the best hardware and build the best PC to play, create and work..

We bring you the latest from hardware, mobile technology and gaming industries in news, reviews, guides and more.

Kaggle is the world’s largest data science community with powerful tools and resources to help you achieve your data science goals.

AMD's long awaited answer to Nvidia's game-prettifying DLSS technology is here. We've had a good old play with FidelityFX Super Resolution (FSR) and it works. In fact, it works flawless

Discover the newest VSR methods and find the most appropriate method for your tasks

Performance benchmarks by UNIGINE

Super resolution is the task of taking an input of a low resolution (LR) and upscaling it to that of a high resolution.

You can find relevant leaderboards in the subtasks below.

( Credit: [MemNet]( MemNet) )

Hello, MSU Graphics & Media Lab Video Group has recently launched two new Super-Resolution Benchmarks. Video Upscalers Benchmark: Quality Enhancement determines the best upscaling methods for increasing video resolution and improving vis...

本文总结超分辨率相关论文，包括图像、视频、盲超分辨率、无参考型图像超分辨率以及基于参考的超级分辨率等。

Data-Free Knowledge Distillation For Image Super-Resolution

本篇文章研究了在移动电话和智能相机中广泛使用的单图像超分辨率（SISR）任务的无数据压缩方法。并在各种数据集和架构上的实验表明，所提出的方法能够在没有原始数据的情况下有效地学习便携式学生网络，例如，在 Set5 的 ×2 超分辨率下，PSNR下降了 0.16dB。

AdderSR: Towards Energy Efficient Image Super-Resolution

本篇文章利用加法神经网络（AdderNets）对单图像的超分辨率问题进行了研究。与卷积神经网络相比，加法神经网络利用加法来计算输出特征，从而避免了传统乘法的大量能量消耗。