Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

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

🌊 A Human-in-the-Loop workflow for creating HD images from text

Video Frame Interpolation & Super Resolution using NVIDIA's TensorRT & Tencent's NCNN inference, beautifully crafted and packaged into a single app

[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr

My VitePress website I made to visually compare the output I created with over 600 different AI upscaling models. Running under https://phhofm.github.io/upscale/

A High Quality (HD / 2K / 4K) Image Generation Using Stable Diffusion and Real-ESR / SwinIR /GFPGAN

A repository of models trained by me!

SwinIR function for VapourSynth

WindSR Dataset contains more than 22,000 pairs of HR/LR wind speed images, which are processed using the NASA's GEOS-5 Nature Run dataset. This dataset is useful for studying super-resolution for data collected using satellites rather natural RGB images.

A multistage text to image framework. Built from a inference-reduced set of min-dalle, glid-3-xl, and SwinIR.

Analysis resources for the Inter IIT Tech Meet 11.0 problem statement by ISRO: The Chandrayaan Moon Mapping Challenge

ImageEditor is a PyQt5-based GUI application for advanced AI-powered image processing. It supports operations such as denoising, super-resolution, background removal, canvas resizing, and format conversion. It integrates powerful models such as SCUNet, SwinIR, and U²-Net.

Lab. Intern with super-resolution

Proposed model on Individual Study (Lab. Intern)

All image enhancement and restoration tools