V
主页
CVPR23 ｜Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior
发布人
code: https://github.com/xl-tang01/UAUDeblur paper: https://arxiv.org/abs/2210.05361 Non-blind deblurring methods achieve decent performance under the accurate blur kernel assumption. Since the kernel uncertainty (i.e. kernel error) is inevitable in practice, semi-blind deblurring is suggested to handle it by introducing the prior of the kernel (or induced) error. However, how to design a suitable prior for the kernel (or induced) error remains challenging. Hand-crafted prior, incorporating domain knowledge, generally performs well but may lead to poor performance when kernel (or induced) error is complex. Data-driven prior, which excessively depends on the diversity and abundance of training data, is vulnerable to out-of-distribution blurs and images. To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios. By organically integrating the respective strengths of deep priors and hand-crafted priors, we propose an unsupervised semi-blind deblurring model which recovers the latent image from the blurry image and inaccurate blur kernel. To tackle the formulated model, an efficient alternating minimization algorithm is developed. Extensive experiments demonstrate the favorable performance of the proposed method as compared to model-driven and data-driven methods in terms of image quality and the robustness to different types of kernel errors.
打开封面
下载高清视频
观看高清视频
视频下载器
Regularized and Neural Approaches to Solve Optimal Transport— Marco Cuturi 2024
【即插即用】CVPR 2024 可形变卷积(DCNv4)
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image
【即插即用】频带注意力FcaNet
即插即用-适用所有图像任务，SPA注意力机制，秒杀Resnet！更少参数，更高指标！
CVPR2024-即插即用多尺度inception卷积
CVPR23 Tutorial | Diffusion models for Inverse problem, 3D vision and Video
OpenAI惊天动地的5天-OpenAI Samaltman （2/3）
即插即用-CVPR顶会卷积模块，SCconv空间、通道双双提升！实现模型暴力涨点！
深度学习 | CV任务通用 | YOLO | CVPR2024 | IDC大核分解卷积和INB轻量高效即插即用模块，适用于目标检测，图像分类，实例分割，语义分割
CVPR2024--StarConv：即插即用的“星模块”卷积
YOLOv11涨点改进 | CVPR 2023 | FSAS和DFFN高效涨点即插即用模块，正确使用轻松暴涨3个点，图像去模糊，目标检测等所有CV任务通用模块
即插即用特征融合模块CAFM，即用即涨点
ICML' 24 | Residual-Conditioned Optimal Transport for Image Restoration
【扩散模型+医学】原作者精讲残差去噪扩散模型RDDM！磁共振扩散成像（MRI）去噪扩散模型的研究
【即插即用】CVPR 2023 SCConv
短短两年就YOLOV8、V9、V10、V11，科研人该如何选择Baseline？
Diffusion Models for Solving Inverse Problems (Jiaming Song, NVIDIA)
即插即用-CVPR可变形注意力机制，1、2、3维数据均可使用，模型指标提升！
耗时三周整理【CVPR2024】可复现论文合集！整理了9个大方向，78篇论文！为你提供新的研究方向、启发论文创新点！-CVPR论文、SCI论文、顶会
2024年诺贝尔物理学奖得主杰弗里·辛顿珍贵访谈：他发明了AI，但又最警惕AI
CVPR2024｜中科院、国科大等五大单位联合推出残差去噪扩散模型(RDDM)：一种用于图像复原和图像生成的统一扩散模型
即插即用-CVPR2024可变形卷积模块DCNv4，更少的参数更高的指标！
强推！不愧是李飞飞，一口把深度学习、计算机视觉、神经网络、图像处理、图像分割、目标检测、物体识别给讲透了，新手小白秒上手！-人工智能/计算机视觉
代码讲解|低频特征提取 超详细版 |CVPR2024 西工大开源！【V1代码讲解009】
【即插即用】CVPR 2023 锚点条带自注意力
【文献汇报】 双流多任务网络
即插即用-2024CVPR最新卷积模块-Inception深度卷积，大核卷积捕捉丰富特征！
最强AI知识库：可分析处理各类文件，内置Gemini 1.5 Pro，强大且免费 | NotebookLM
Why Does Diffusion Work Better than Auto-Regression?
代码讲解|通道加权方案 CVPR2024热点！附Transformer和CNN两种【V1代码讲解012】
AAAI 2024 创新点看过来，动态频域fft模块，即插即用
Qwen大模型本地部署教程！教你本地微调一个法律大模型，无需GPU，只要5G内存！附安装包和微调文档！
CVPR2024 残差去噪扩散模型（自用转载）
全球100位伟大女性之一李飞飞演讲：我为什么投身AI事业？
CVPR2024 DCNv4:新一代高效的可变形卷积！
CVPR 2024 Highlight 英伟达 通用的新颖对象的6D位姿估计与跟踪 FoundationPose
13分钟速通yolov11，使用自己的数据集从环境搭建到模型训练、推理、导出
24年论文打不过22年的，跑通baseline就能发论文？
【即插即用模块分享】scSE注意力
