167 Open source projects that are alternatives of or similar to Awesome Eccv2020 Low Level Vision

ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks, published in ECCV 2018) implemented in Tensorflow 2.0+. This is an unofficial implementation. With Colab.

SwinIR: Image Restoration Using Swin Transformer (official repository)

Image Restoration Toolbox (PyTorch). Training and testing codes for USRNet, DnCNN, FFDNet, SRMD, DPSR, ESRGAN

Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.

Applying SRGAN technique implemented in https://github.com/zsdonghao/SRGAN on videos to super resolve them.

VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.

A tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", a deep learning based Single-Image Super-Resolution (SISR) model.

The official pytorch implemention of the CVPR paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution".

TensorFlow implementation of the Efficient Sub-Pixel Convolutional Neural Network

Bicubic interpolation for images (Python)

Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)

Generative Adversarial Network for single image super-resolution in high content screening microscopy images

Caffe implementation of "Fast and Accurate Single Image Super-Resolution via Information Distillation Network" (CVPR 2018)

SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow

Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution

Image Super-Resolution Using Deep Convolutional Networks in Tensorflow https://arxiv.org/abs/1501.00092v3

Pytorch implementation for SRDenseNet (ICCV2017)

The py version of toflow → https://github.com/anchen1011/toflow

[CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference

Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)

DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal images (ESA PROBA-V challenge)

Hyperspectral Image Spatial Super-Resolution via 3D-Full-Convolutional-Neural-Network

A survey of recent application of deep learning on super-resolution tasks

Image Super-Resolution for Anime-Style Art

Keras implementation of EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

Super-resolution (SR) is a method of creating images with higher resolution from a set of low resolution images.

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

An Unofficial PyTorch Implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Tensorflow 2.x based implementation of EDSR, WDSR and SRGAN for single image super-resolution

A generic framework which implements some famouts super-resolution models

Tensorflow implementation of pixel-recursive-super-resolution(Google Brain paper: https://arxiv.org/abs/1702.00783)

只要蘊藏著想成為真物的意志，偽物就比真物還要來得真實。

Super Resolution of picture images using deep learning

Super-Resolution imaging with Convolutional Neural Network library for G++, Non-OpenCV model.

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)

Neighborhood Regression for Edge-Preserving Image Super-Resolution (ICASSP 2015)

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)

A collection of tools for painting super-resolution images

Tensorflow implementation of Enhanced Deep Residual Networks for Single Image Super-Resolution

This is an official implementation of Unfolding the Alternating Optimization for Blind Super Resolution

3D super-resolution using Generative Adversarial Networks

A TensorFlow-based image super-resolution model considering both quantitative and perceptual quality

TOFlow: Video Enhancement with Task-Oriented Flow

Single image example-based super resolution. Improves the spatial and temporal resolution of an image using a direct mapping of LR HR patch pairs. C++, openCV.

Scale-wise Convolution for Image Restoration

Super Resolution for Anime image, lightweight implementation

A modern PyTorch implementation of SRGAN

PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN

Official implementation: Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution, CVPR 2020

Test Time Augmentation (TTA) wrapper for computer vision tasks: segmentation, classification, super-resolution, ... etc.

Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination (CVPR, 2019)

Latest development of ISR/VSR. Papers and related resources, mainly state-of-the-art and novel works in ICCV, ECCV and CVPR about image super-resolution and video super-resolution.

Matlab reimplementation of SCNSR

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018.