Awesome-diffusion-model-for-image-processing

Awesome-diffusion-model-for-image-processing

扩散模型在图像处理领域的最新进展与应用汇总

本项目汇总了扩散模型在图像处理领域的最新研究进展,涵盖图像复原、增强、编码和质量评估等方面。重点关注图像超分辨率、修复和去噪等任务,提供全面的调查报告和定期更新的研究成果。项目收录了大量相关开源代码和数据集资源,为研究人员提供了重要的参考信息。

扩散模型图像处理超分辨率图像复原深度学习Github开源项目
<p align="center"> <img src="./figures/framework.png" alt="image" style="width:1000px;"> </p>

Purpose: We aim to provide a summary of diffusion model-based image processing, including restoration, enhancement, coding, and quality assessment. More papers will be summarized.

Xin Li, Yulin Ren, Xin Jin, Cuiling Lan, Xingrui Wang, Wenjun Zeng, Xinchao Wang, Zhibo Chen

University of Science and Technology of China (USTC), National University of Singapore (NUS), Microsoft Research Asia (MSRA), Eastern Institute of Technology (EIT)

Brief intro: The survey for diffusion model-based IR has been released.

arXiv visitors

:bookmark: News!!!

  • 2023-09-19: Updated new related works before 15/09/2023 in this GitHub.
  • 2023-11-24: Updated new related works before 10/11/2023 in this GitHub.
  • 2023-12-25: Updated new related works before 25/12/2023 in this GitHub.
  • 2024-01-25: Updated new related works before 25/01/2024 in this GitHub.
  • 2024-03-25: Updated new related works before 25/03/2024 in this GitHub.
  • 2024-04-25: Updated new related works before 25/04/2024 in this GitHub.
  • 2024-06-25: Updated new related works before 25/06/2024 in this GitHub.
  • 2024-08-25: Updated new related works before 25/08/2024 in this GitHub.

📌 About new works. If you want to incorporate your studies (e.g., the link of paper or project) on diffusion model-based image processing in this repository. Welcome to raise an issue or email us. We will incorporate it into this repository and our survey report as soon as possible.

🌟 Features

  • Survey for diffusion model-based Image Restoration (Arxiv version is released)
  • Summary for diffusion model-based Image/Video Compression
  • Summary for diffusion model-based Quality Assessment

Diffusion model-based Image Restoration/Enhancement

Table of contents

<!-- - [Survey paper](#survey-paper) - [Table of contents](#table-of-contents) --> <!-- - [Diffusion model for Image/video compression](#compression) --> <!-- - [Recommended Datasets](#recommended-datasets) - [All Datasets](#all-datasets) -->

Image Super-Resolution

ModelsPaperFirst AuthorTraining WayVenueTopicProject
SR3Image super-resolution via iterative refinementChitwan SahariaSupervisedTPAMI2022Super-resolutionStars
SRDiffSRDiff: Single Image Super-Resolution with Diffusion Probabilistic ModelsHaoying LiSupervisedNeurocomputing 2022Super-resolutionStars
SDE-SRFace super-resolution using stochastic differential equationsMarcelo dos SantosSupervisedSIBGRAPI 2022Super-resolutionStars
IDMImplicit diffusion models for continuous super-resolutionSicheng GaoSupervisedCVPR2023Super-resolutionStars
PromptSRImage Super-Resolution with Text Prompt DiffusionZheng ChenSupervisedPreprint'23Super-resolutionStars
DiffIRDiffIR: Efficient diffusion model for image restorationBin XiaSupervisedICCV 2023Super-resolutionStars
CDMCascaded Diffusion Models for High Fidelity Image GenerationJonathan HoSupervisedJ.Mach.Learn.Res 2022Super-resolution
StableSRExploiting diffusion prior for real-world image super-resolutionJianyi WangSupervisedPreprint'23Real-World Super-resolutionStars
ResShiftResShift: Efficient Diffusion Model for Image Super-resolution by Residual ShiftingZongsheng YueSupervisedNeurIPS 2023Real-World Super-resolutionStars
ECDPEfficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolutionYutao YuanSupervisedAAAI 2024Super-resolutionStars
SinSRSinSR: Diffusion-Based Image Super-Resolution in a Single StepYufei WangSupervisedCVPR 2024Real-World Super-resolutionStars
TextDiffTextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-ResolutionBaolin LiuSupervisedPreprint'23Super-resolutionStars
PASDPixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized StylizationTao YangSupervisedPreprint'23Super-resolutionStars
CCSRImproving the Stability of Diffusion Models for Content Consistent Super-ResolutionLingchen SunSupervisedPreprint'23Super-resolutionStars
EDiffSREDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-ResolutionYi XiaoSupervisedIEEE TGRSSuper-resolutionStars
SeeSRSeeSR: Towards Semantics-Aware Real-World Image Super-ResolutionRongyuan WuSupervisedPreprint'23Super-resolutionStars
CoSeRCoSeR: Bridging Image and Language for Cognitive Super-ResolutionHaoze SunSupervisedCVPR 2024Super-resolutionStars
BI-DiffSRBinarized Diffusion Model for Image Super-ResolutionZheng ChenSupervisedPreprint'24Super-resolutionStars
DaLPSRDaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-ResolutionAiwen JiangSupervisedPreprint'24Super-resolution
FDDiffFrequency-Domain Refinement with Multiscale Diffusion for Super ResolutionXingjian WangSupervisedPreprint'24Super-resolution
PartDiffPartDiff: Image Super-resolution with Partial Diffusion ModelsKai ZhaoSupervisedPreprint'23Super-resolution
DeeDSRDeeDSR: Towards Real-World Image Super-Resolution via Degradation-Aware Stable DiffusionChunyang BiSupervisedPreprint'24(Real-World) Super-resolution
SR3+Denoising diffusion probabilistic models for robust image super-resolution in the wildHshmat SahakSupervisedPreprint'23(Real-World) Super-resolution
DKPA Dynamic Kernel Prior Model for Unsupervised Blind Image Super-ResolutionZhixiong YangSupervisedCVPR 2024(Real-World) Super-resolutionStars
DiwaWaving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-ResolutionBrian MoserSupervisedPreprint'23Super-resolutionStars
YODAYODA: You Only Diffuse Areas. An Area-Masked Diffusion Approach For Image Super-ResolutionBrian B. MoserSupervisedPreprint'23Super-resolution
CDPMSRCDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-ResolutionAxi NiuSupervisedPreprint'23Super-resolution
ACDPMSRACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-ResolutionAxi NiuSupervisedPreprint'23Super-resolution
ResDiffResDiff: Combining cnn and diffusion model for image superresolutionShuyao ShangSupervisedPreprint'23Super-resolution
OSEDiffOne-Step Effective Diffusion Network for Real-World Image Super-ResolutionRongyuan WuSupervisedPreprint'24Super-resolution
DiffTSRDiffusion-based Blind Text Image Super-ResolutionYuzhe ZhangSupervisedCVPR 2024Super-resolution
SAM-DiffSRSAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-ResolutionChengcheng WangSupervisedPreprint'24Super-resolutionStars
BlindDiffBlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-ResolutionFeng LiSupervisedPreprint'24Super-resolutionStars
XPSRXPSR: Cross-modal Priors for Diffusion-based Image Super-ResolutionYunpeng QuSupervisedPreprint'24Super-resolutionStars
--Text-guided Explorable Image Super-resolutionKanchana Vaishnavi GandikotaZero-shotPreprint'24

编辑推荐精选

讯飞智文

讯飞智文

一键生成PPT和Word,让学习生活更轻松

讯飞智文是一个利用 AI 技术的项目,能够帮助用户生成 PPT 以及各类文档。无论是商业领域的市场分析报告、年度目标制定,还是学生群体的职业生涯规划、实习避坑指南,亦或是活动策划、旅游攻略等内容,它都能提供支持,帮助用户精准表达,轻松呈现各种信息。

AI办公办公工具AI工具讯飞智文AI在线生成PPTAI撰写助手多语种文档生成AI自动配图热门
讯飞星火

讯飞星火

深度推理能力全新升级,全面对标OpenAI o1

科大讯飞的星火大模型,支持语言理解、知识问答和文本创作等多功能,适用于多种文件和业务场景,提升办公和日常生活的效率。讯飞星火是一个提供丰富智能服务的平台,涵盖科技资讯、图像创作、写作辅助、编程解答、科研文献解读等功能,能为不同需求的用户提供便捷高效的帮助,助力用户轻松获取信息、解决问题,满足多样化使用场景。

热门AI开发模型训练AI工具讯飞星火大模型智能问答内容创作多语种支持智慧生活
Spark-TTS

Spark-TTS

一种基于大语言模型的高效单流解耦语音令牌文本到语音合成模型

Spark-TTS 是一个基于 PyTorch 的开源文本到语音合成项目,由多个知名机构联合参与。该项目提供了高效的 LLM(大语言模型)驱动的语音合成方案,支持语音克隆和语音创建功能,可通过命令行界面(CLI)和 Web UI 两种方式使用。用户可以根据需求调整语音的性别、音高、速度等参数,生成高质量的语音。该项目适用于多种场景,如有声读物制作、智能语音助手开发等。

Trae

Trae

字节跳动发布的AI编程神器IDE

Trae是一种自适应的集成开发环境(IDE),通过自动化和多元协作改变开发流程。利用Trae,团队能够更快速、精确地编写和部署代码,从而提高编程效率和项目交付速度。Trae具备上下文感知和代码自动完成功能,是提升开发效率的理想工具。

AI工具TraeAI IDE协作生产力转型热门
咔片PPT

咔片PPT

AI助力,做PPT更简单!

咔片是一款轻量化在线演示设计工具,借助 AI 技术,实现从内容生成到智能设计的一站式 PPT 制作服务。支持多种文档格式导入生成 PPT,提供海量模板、智能美化、素材替换等功能,适用于销售、教师、学生等各类人群,能高效制作出高品质 PPT,满足不同场景演示需求。

讯飞绘文

讯飞绘文

选题、配图、成文,一站式创作,让内容运营更高效

讯飞绘文,一个AI集成平台,支持写作、选题、配图、排版和发布。高效生成适用于各类媒体的定制内容,加速品牌传播,提升内容营销效果。

热门AI辅助写作AI工具讯飞绘文内容运营AI创作个性化文章多平台分发AI助手
材料星

材料星

专业的AI公文写作平台,公文写作神器

AI 材料星,专业的 AI 公文写作辅助平台,为体制内工作人员提供高效的公文写作解决方案。拥有海量公文文库、9 大核心 AI 功能,支持 30 + 文稿类型生成,助力快速完成领导讲话、工作总结、述职报告等材料,提升办公效率,是体制打工人的得力写作神器。

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

下拉加载更多