基于数字图像处理和深度学习的图像质量提升 使用PRIDNet 和SRCNN 进行去噪和超分. 用 SpringBoot+Mybatis plus+Vue进行界面和后端设计

Scalable Super Resolution in pure rust

image transformation

AI-powered Image Resize Tool

Upscale an illustration and increase details

Super-Resolution models implemented in PyTorch Lightning

Image super resolution using with Deep Convolutional Neural Networks

Reimplementation of SRCNN

TensorFlow implementation of SRCNN

This project implements SRCNN (Super-Resolution Convolutional Neural Network) for single-image super-resolution. The algorithm is trained on a dataset of low-resolution and high-resolution image pairs, and can improve the visual quality of low-resolution images by generating high-resolution images from them.

C++ Implementation of Image Super-Resolution with Convolutional Neural Network with OpenCV adn OpenMP [Discontinued]

Critical Analysis and Implementation of SRCNN (part of Deep Learning and Computer Vision module)

Deep Learning-based super resolution image reconstruction

A Super-Resolution Convolutional Neural Network builds for artwork, anime, and illustration. Senior Project - Artwork Enlargement and Quality Improvement using Machine Learning. ICITEE 2021 - Enhancement of Anime Imaging Enlargement Using Modified Super-Resolution CNN.

Implemented SRCNN with Pytorch from scratch & trained with custom dataset

A Super Sampling model created using the SRCNN method proposed by Chao Dong, Chen Change Loy in 2015. It uses Convolutional Networks to identify features and uses "Depth-To-Feature" technique in the end to generate a high resolution image of a given low resolution input. The model is trained and tested on BSDS500 dataset.

Pytorch based implementation of SRCNN for single image super-resolution

Tensorflow 2.x based implementation of SRCNN for single image super-resolution

Implementation of EDSR, ESPCN, LAPSRN, SRCNN, SRGAN and WDSR for single image super-resolution (SISR) based on Tensorflow 2.x for CMU's 10-707 Advanced Deep Learning Final Project