首页/论文/1809.04693

arXiv 1809.046932018-09-12cs.CVeess.IV

An Online Plug-and-Play Algorithm for Regularized Image Reconstruction

Washington University in St. Louis（圣路易斯华盛顿大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

Yu Sun, Brendt Wohlberg, Ulugbek S. Kamilov

DOI：: 10.1109/TCI.2019.2893568

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Plug-and-play priors (PnP) is a powerful framework for regularizing imaging inverse problems by using advanced denoisers within an iterative algorithm. Recent experimental evidence suggests that PnP algorithms achieve state-of-the-art performance in a range of imaging applications. In this paper, we introduce a new online PnP algorithm based on the iterative shrinkage/thresholding algorithm (ISTA). The proposed algorithm uses only a subset of measurements at every iteration, which makes it scalable to very large datasets. We present a new theoretical convergence analysis, for both batch and online variants of PnP-ISTA, for denoisers that do not necessarily correspond to proximal operators. We also present simulations illustrating the applicability of the algorithm to image reconstruction in diffraction tomography. The results in this paper have the potential to expand the applicability of the PnP framework to very large and redundant datasets.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Regularized Fourier Ptychography using an Online Plug-and-Play Algorithm

Washington University in St. Louis（圣路易斯华盛顿大学）；Boston University（波士顿大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

The plug-and-play priors (PnP) framework has been recently shown to achieve state-of-the-art results in regularized image reconstruction by leveraging a sophisticated denoiser within an iterative algorithm. In this paper, we propose a new online PnP algorithm for Fourier ptychographic microscopy (FPM) based on the fast iterative shrinkage/threshold algorithm (FISTA). Specifically, the proposed algorithm uses only a subset of measurements, which makes it scalable to a large set of measurements. We validate the algorithm by showing that it can lead to significant performance gains on both simula…

2018-11-02cs.CV

Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibrium

Purdue University（普渡大学）

Regularized inversion methods for image reconstruction are used widely due to their tractability and ability to combine complex physical sensor models with useful regularity criteria. Such methods motivated the recently developed Plug-and-Play prior method, which provides a framework to use advanced denoising algorithms as regularizers in inversion. However, the need to formulate regularized inversion as the solution to an optimization problem limits the possible regularity conditions and physical sensor models. In this paper, we introduce Consensus Equilibrium (CE), which generalizes regulari…

2018-06-13cs.CVmath.OC

PUF：用于在线3D场景图生成的即插即用不确定性感知融合

PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation

Leibniz Universität Hannover（汉诺威莱布尼茨大学）；Istituto Italiano di Tecnologia（意大利技术研究院）；University of Bath（巴斯大学）

研究在线3D场景图生成中不确定性问题，提出PUF框架，将节点关联概率化，用狄利克雷证据积累分配证据，可选先验补全边，在不同后端实例化有改进，实验表明该方法优于现有方法，确立不确定性感知融合范式。

2026-07-09cs.CV

Deep Plug-and-play Prior for Low-rank Tensor Completion

University of Electronic Science and Technology of China（电子科技大学）；Southwestern University of Finance and Economics（西南财经大学）；Xi’an Jiaotong University（西安交通大学）

Multi-dimensional images, such as color images and multi-spectral images, are highly correlated and contain abundant spatial and spectral information. However, real-world multi-dimensional images are usually corrupted by missing entries. By integrating deterministic low-rankness prior to the data-driven deep prior, we suggest a novel regularized tensor completion model for multi-dimensional image completion. In the objective function, we adopt the newly emerged tensor nuclear norm (TNN) to characterize the global low-rankness prior of the multi-dimensional images. We also formulate an implicit…

2020-05-04cs.CVeess.IV

GaussianTrimmer: 3DGS 分割的在线边界修剪

GaussianTrimmer: Online Trimming Boundaries for 3DGS Segmentation

Peking University Shenzhen Graduate School（北京大学深圳研究生院）

GaussianTrimmer通过生成虚拟相机和基于2D分割结果的原语层面修剪，提升3D高斯分割的边界质量。

2026-01-19cs.CVeess.IV

Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation

Purdue University（普渡大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Air Force Research Laboratory（美国空军研究实验室）

Many material and biological samples in scientific imaging are characterized by non-local repeating structures. These are studied using scanning electron microscopy and electron tomography. Sparse sampling of individual pixels in a 2D image acquisition geometry, or sparse sampling of projection images with large tilt increments in a tomography experiment, can enable high speed data acquisition and minimize sample damage caused by the electron beam. In this paper, we present an algorithm for electron tomographic reconstruction and sparse image interpolation that exploits the non-local redundanc…

2015-12-23cs.CVeess.IV

更多相关论文收起更多论文

利用即插即用状态空间模型与类条件离散化混合增强在线持续学习

Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization

Harbin Institute Of Technology（哈尔滨工业大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Harbin Institute Of Technology (Shenzhen)（哈尔滨工业大学（深圳））；University of Oxford（牛津大学）

提出即插即用模块S6MOD，通过离散化混合和类条件路由算法动态调整状态空间模型参数，显著提升在线持续学习的模型适应性与性能。

2024-12-24cs.AIcs.CVcs.LG

基于评分的turbo信息传递用于即插即用压缩图像恢复

Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery

Department of Information Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR（信息工程系，香港中文大学（深圳校区））；National Key Lab. of Wireless Commun., Uni. of Electronic Sci. and Tech. of China, Chengdu, China（无线通信国家重点实验室，电子科技大学，成都，中国）

本文提出了一种基于评分的turbo信息传递框架，利用评分建模与经验贝叶斯最优去噪的关系，提升压缩图像恢复的性能-复杂度权衡。

2025-12-15cs.CVeess.IVeess.SP

将重加权最小二乘法与即插即用扩散先验相结合用于含噪图像复原

Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration

本文提出一种基于扩散先验的即插即用图像复原框架，通过广义高斯尺度混合损失和迭代重加权最小二乘法，有效去除脉冲噪声等非高斯噪声。

2025-11-10cs.CV

SelfReg-UNet: 用于医学图像分割的自正则化UNet

SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation

School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；McKeley School of Engineering, Washington University in St. Louis（圣路易斯华盛顿大学麦凯莱工程学院）；School of Computing, Clemson University（克莱姆森大学计算学院）

针对UNet因非对称监督产生无关特征、特征图存在冗余的问题，提出SelfReg-UNet，通过解码器末层额外监督与特征蒸馏优化，可即插即用提升UNet在医学图像分割任务上的性能。

2024-06-21cs.CVeess.IV

Watch and Match: Supercharging Imitation with Regularized Optimal Transport

New York University（纽约大学）

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert demonstrations, an agent alternatively infers a reward function and the associated optimal policy. However, such IRL approaches often require substantial online interactions for complex control problems. In this work, we present Regularized Optimal Transport (ROT), a new imitation learning algorithm that builds on recent advances in optimal transport based trajectory-mat…

2023-02-20cs.AIcs.CVcs.LG