[CVPR 2024] CoSeR: Bridging Image and Language for Cognitive Super-Resolution

Let us democratise high-resolution generation! (CVPR 2024)

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

效果更好的补帧软件，显存占用更小，是DAIN速度的10-25倍，包含抽帧处理，去除动漫卡顿感

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

Official codes of CCSR: Improving the Stability of Diffusion Models for Content Consistent Super-Resolution

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

Code for DesignEdit

APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)

Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

Official code for DiFaReli

neosr is a framework for training real-world single-image super-resolution networks.

Bring portraits to life!