Video Super-Resolution
132 papers with code • 15 benchmarks • 13 datasets
Video Super-Resolution is a computer vision task that aims to increase the resolution of a video sequence, typically from lower to higher resolutions. The goal is to generate high-resolution video frames from low-resolution input, improving the overall quality of the video.
( Image credit: Detail-revealing Deep Video Super-Resolution )
Benchmarks
These leaderboards are used to track progress in Video Super-Resolution
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Video Super-Resolution models and implementationsDatasets
Vimeo90K
MSU SR-QA Dataset
MSU Video Super Resolution Benchmark: Detail Restoration
MSU Video Upscalers: Quality Enhancement
MSU Super-Resolution for Video Compression
Inter4K
TbD-3D
TbD
Falling Objects
Most implemented papers
Image Super-Resolution Using Deep Convolutional Networks
nagadomi/waifu2x
•
•
We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
xinntao/ESRGAN
•
•
To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
This means that the super-resolution (SR) operation is performed in HR space.
XGBoost: A Scalable Tree Boosting System
In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges.
Deep Back-Projection Networks For Super-Resolution
sanghyun-son/EDSR-PyTorch
•
•
CVPR 2018
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output.
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
thunil/TecoGAN
•
•
Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution.
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
xinntao/EDVR
•
•
In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges.
SwinIR: Image Restoration Using Swin Transformer
In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Lornatang/VDSR-PyTorch
•
•
CVPR 2016
We present a highly accurate single-image super-resolution (SR) method.
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images.
