[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

[ICML 2024] EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

[CVPR 2024 Highlight] Enhancing Video Super-Resolution via Implicit Resampling-based Alignment.

🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook

a family of versatile and state-of-the-art video tokenizers.

[arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization

Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?

Code for BLT research paper

Official Jax Implementation of MaskGIT

XQ-GAN🚀: An Open-source Image Tokenization Framework for Autoregressive Generation

collection of diffusion model papers categorized by their subareas

FQGAN: Factorized Visual Tokenization and Generation

Calculate quality metrics with FFmpeg (SSIM, PSNR, VMAF, VIF)

Visualizes Video Quality Metrics (PSNR, SSIM & VMAF) calculated by ffmpeg.exe

Perceptual video quality assessment based on multi-method fusion.

Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

HunyuanVideo: A Systematic Framework For Large Video Generation Model

This repo contains the code for 1D tokenizer and generator

A suite of image and video neural tokenizers

Open-Sora: Democratizing Efficient Video Production for All

Generative Models by Stability AI