div2k

🔥 Real-time Super Resolution enhancement (4x) with content loss and relativistic adversarial optimization 🔥

A TensorFlow implementation of ESRGAN

A tensorflow-based implementation of SISR using EDSR, SRResNet, and SRGAN

使用PaddlePaddle复现Real-ESRGAN

This repository contains source code implementation of assignments for NTU's MSAI course AI6126 on Advanced Computer Vision (2020 Sem 1).

Reimplementation of SRGAN using TensorFlow 2

Tensorflow Implementation of enhanced deep super-resolution network (EDSR) and Super Resolution Generative Adversarial Networks(SRGAN) Paper

GCS specific notebooks and scripts to download VOC 2007, COCO 2017 and DIV2K Datasets and create TFRecords.

Implementation of image super-resolution using EDSR and WDSR on DIV2k Dataset

Block-wise confidence-aware CNN that predicts the compression quality level (e.g. JPEG quality factor) of an image in real time — official TensorFlow implementation of the BMVC 2021 paper

This repository features an image sharpening pipeline using Knowledge Distillation. A high-capacity Restormer acts as the teacher model, while a lightweight Mini-UNet is trained as the student to mimic its performance.

Reimplementation of SRGAN & SRCNN Using DIV2K

Prepare training data for NTIRE SR Challenge

A novel framework for Single Image Super Resolution using Generative Adversarial Network (GAN), namely "Wide Activation with Enhanced Perception Super Resolution GAN (WAEP SRGAN)".

Restoring old images using deep learning. Initial code is adopted from Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising by K. Zhang, et. al By: Maya Hussein & Nada Badawi

Implementation of image super-resolution using SRResNet on DIV2k Dataset

AutoSteganography is a tool for encoding and decoding stegnographic images using Autoencoders

This repository contains implementations, training routines, and evaluation scripts for various Single Image Super-Resolution (SISR) models.

Reimplement Super Resolution CNN by using DIV2K datasets

Lightweight CNN-Swin Transformer and EDSR models for single-image super-resolution using PyTorch, with DIV2K evaluation and Apple Silicon MPS support.