SwinIR:使用 Swin Transformer 进行图像恢复(官方仓库)
image-super-resolution 开源项目推荐(141 个)
image-super-resolution 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 141 个仓库🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
HYPIR:Harnessing Diffusion-Yielded Score Priors for Image Restoration(SIGGRAPH 2025)的正式实施
Official Code for “Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling” ICLR 2026
[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution
[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
PyTorch implementation of Image Super-Resolution Using Deep Convolutional Networks (ECCV 2014)
ACG2vec(Anime Comics Games to vector)致力于打造一个结合 ACG 与深度学习的游乐场。(文本语义检索、以图搜图、语义搜图、图片超分辨率、推荐系统)
A Repository for Diffusion-Model-related Papers in Low-level Vision
low-light💡 image enhancement
A Flexible and Unified Image Restoration Framework (PyTorch), including state-of-the-art image restoration model. Such as NAFNet, Restormer, MPRNet, MIMO-UNet, SCUNet, SwinIR, HINet, etc. ⭐⭐⭐⭐⭐⭐
PyTorch implementation of Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network implemented in Keras
A Collection of Low Level Vision Research Groups
Lightweight Image Super-Resolution with Enhanced CNN (Knowledge-Based Systems,2020)
Image super resolution models for PyTorch.
Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)
Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)
Camera Lens Super-Resolution in CVPR 2019
Code for Non-Local Recurrent Network for Image Restoration (NeurIPS 2018)
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/image-super-resolution。
- 该话题在 GitHub 上共有 141 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1.9 万 Star,覆盖 2 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。