汇总了自2024年以来新提出的高质量图像修复工作，包含扩散模型、transformer、mamba、sam等最前沿的技术，其中一些是ICLR、ICML、CVPR、ECCV、ACM MM 2024年的新作。
这里是第三部分，还有两部分请参阅。
这篇博客先做简单汇总，后续我还会逐一阅读和学习，并逐一写详细的博客介绍。
目录
[Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration](#Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration)
[Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model](#Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model)
[Learning Diffusion Texture Priors for Image Restoration](#Learning Diffusion Texture Priors for Image Restoration)
[A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](#A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting)
[BrushNet : A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](#BrushNet : A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion)
[PowerPaint: A Versatile Image Inpainting Model](#PowerPaint: A Versatile Image Inpainting Model)
[Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model](#Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model)
[Plug-and-Play image restoration with Stochastic deNOising REgularization](#Plug-and-Play image restoration with Stochastic deNOising REgularization)
[ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement](#ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement)
[Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration](#Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration)
[A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](#A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting)
[SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning](#SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning)
Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration
https://arxiv.org/pdf/2312.02918
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Learning Diffusion Texture Priors for Image Restoration
A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
https://arxiv.org/pdf/2312.03594
BrushNet : A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
PowerPaint: A Versatile Image Inpainting Model
eccv 2024
https://github.com/open-mmlab/PowerPaint
Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model
https://arxiv.org/pdf/2407.16982
Plug-and-Play image restoration with Stochastic deNOising REgularization
ICML 2024
https://arxiv.org/pdf/2402.01779
ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement
https://arxiv.org/pdf/2407.17705
Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration
https://arxiv.org/pdf/2407.03636
A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
https://arxiv.org/pdf/2312.03594
SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning
https://arxiv.org/pdf/2401.11847v1
