arXiv 2111.108922021-11-21eess.IVcs.CV

Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP

The University of Iowa（爱荷华大学）

Maneesh John, Hemant Kumar Aggarwal, Qing Zou, Mathews Jacob

英文摘要：

Deep learning algorithms that rely on extensive training data are revolutionizing image recovery from ill-posed measurements. Training data is scarce in many imaging applications, including ultra-high-resolution imaging. The deep image prior (DIP) algorithm was introduced for single-shot image recovery, completely eliminating the need for training data. A challenge with this scheme is the need for early stopping to minimize the overfitting of the CNN parameters to the noise in the measurements. We introduce a generalized Stein's unbiased risk estimate (GSURE) loss metric to minimize the overfitting. Our experiments show that the SURE-DIP approach minimizes the overfitting issues, thus offering significantly improved performance over classical DIP schemes. We also use the SURE-DIP approach with model-based unrolling architectures, which offers improved performance over direct inversion schemes.

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

SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate

Stanford University（斯坦福大学）

Convolutional neural networks (CNN) have emerged as a powerful tool for solving computational imaging reconstruction problems. However, CNNs are generally difficult-to-understand black-boxes. Accordingly, it is challenging to know when they will work and, more importantly, when they will fail. This limitation is a major barrier to their use in safety-critical applications like medical imaging: Is that blob in the reconstruction an artifact or a tumor? In this work we use Stein's unbiased risk estimate (SURE) to develop per-pixel confidence intervals, in the form of heatmaps, for compressive se…

2021-04-20cs.CVeess.IV

奇异值的平滑硬阈值与Stein无偏风险估计

Smooth Hard-Thresholding for Singular Values with Stein's Unbiased Risk Estimate

Imperial College London（伦敦帝国理工学院）

针对低秩矩阵去噪，提出基于Stein无偏风险估计的平滑硬阈值谱估计器，解决传统硬阈值不连续问题，并证明其无偏风险估计性质。

2026-10-16cs.NAeess.IVeess.SP

Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning

Estimators based on non-convex sparsity-promoting penalties were shown to yield state-of-the-art solutions to the magneto-/electroencephalography (M/EEG) brain source localization problem. In this paper we tackle the model selection problem of these estimators: we propose to use a proxy of the Stein's Unbiased Risk Estimator (SURE) to automatically select their regularization parameters. The effectiveness of the method is demonstrated on realistic simulations and $30$ subjects from the Cam-CAN dataset. To our knowledge, this is the first time that sparsity promoting estimators are automaticall…

2021-10-28eess.IVeess.SPmath.OC

Fixed Point Iterations for SURE-based PSF Estimation for Image Deconvolution

Stein's unbiased risk estimator (SURE) has been shown to be an effective metric for determining optimal parameters for many applications. The topic of this article is focused on the use of SURE for determining parameters for blind deconvolution. The parameters include those that define the shape of the point spread function (PSF), as well as regularization parameters in the deconvolution formulas. Within this context, the optimal parameters are typically determined via a brute for search over the feasible parameter space. When multiple parameters are involved, this parameter search is prohibit…

2022-02-26cs.NAeess.IVmath.NA

无偏风险估计器在无监督磁共振图像去噪中的自适应扩展

Adaptive Extensions of Unbiased Risk Estimators for Unsupervised Magnetic Resonance Image Denoising

University of Arkansas（阿肯色大学）

本文针对医学成像中缺乏无噪声真实图像的问题，提出并基准测试了SURE、eSURE及新颖的ePURE等无监督学习策略，在受高斯和泊松噪声影响的MRI数据上验证了其有效性与鲁棒性。

2024-07-23cs.CVeess.IV

图像去噪的无监督非局部方法的统一视角：NL-Ridge 方法

Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach

Inria Centre Rennes - Bretagne Atlantique（法国国家信息与自动化研究所雷恩-布列塔尼大西洋中心）；CNRS Institut Curie（法国国家科学研究中心居里研究所）；PSL Research University（巴黎文理研究大学）；Sorbonne Université（索邦大学）

本文提出图像去噪无监督非局部方法的统一视角 NL-Ridge，通过结合 SURE 和内部适应概念的两步算法，利用多元 Ridge 回归计算闭式聚合权重，在概念更简单的同时性能优于 BM3D 等先进无监督去噪器。

2022-03-01cs.CVeess.IV

更多相关论文收起更多论文

通过重复到重复学习实现自监督噪声自适应MRI去噪

Self-Supervised Noise Adaptive MRI Denoising via Repetition to Repetition (Rep2Rep) Learning

Rep2Rep学习通过重复到重复的方法实现自监督噪声自适应MRI去噪，优于MC-SURE并在不同噪声水平下表现稳健。

2025-04-24eess.IV

Image Restoration by Deep Projected GSURE

Tel-Aviv University（特拉维夫大学）；Ulsan National Institute of Science and Technology（蔚山国立科学技术院）；Weizmann Institute of Science（魏茨曼科学研究所）

Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of these techniques, which train CNNs using external data, are restricted to the observation models that have been used in the training phase. A recent alternative that does not have this drawback relies on learning the target image using internal learning. One such prominent example is the Deep Image Prior (DIP) technique that trains a network directly on the …

2021-02-04cs.CVeess.IV

Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements

University of Edinburgh（爱丁堡大学）

Deep networks provide state-of-the-art performance in multiple imaging inverse problems ranging from medical imaging to computational photography. However, most existing networks are trained with clean signals which are often hard or impossible to obtain. Equivariant imaging (EI) is a recent self-supervised learning framework that exploits the group invariance present in signal distributions to learn a reconstruction function from partial measurement data alone. While EI results are impressive, its performance degrades with increasing noise. In this paper, we propose a Robust Equivariant Imagi…

2022-03-15cs.CVeess.IVeess.SP

Boosting CNN beyond Label in Inverse Problems

KAIST（韩国科学技术院）；Samsung Advanced Institute of Technology（三星先进技术研究院）

Convolutional neural networks (CNN) have been extensively used for inverse problems. However, their prediction error for unseen test data is difficult to estimate a priori since the neural networks are trained using only selected data and their architecture are largely considered a blackbox. This poses a fundamental challenge to neural networks for unsupervised learning or improvement beyond the label. In this paper, we show that the recent unsupervised learning methods such as Noise2Noise, Stein's unbiased risk estimator (SURE)-based denoiser, and Noise2Void are closely related to each other …

2019-06-18cs.CVcs.LGeess.IV

利用含噪数据学习的基于分数的生成先验求解逆问题

Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data

Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校电气与计算机工程系）；Intel Corporation（英特尔公司）

提出SURE-Score方法，利用含噪数据学习基于分数的生成先验，通过Stein无偏风险估计联合去噪与分数匹配，应用于压缩MIMO信道估计和加速MRI重建，在低信噪比下取得竞争性性能。

2023-05-02cs.LGeess.IVeess.SP

Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images

Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Kim Jaechul Graduate School of AI（金在哲人工智能研究生院）

Recently, there has been extensive research interest in training deep networks to denoise images without clean reference. However, the representative approaches such as Noise2Noise, Noise2Void, Stein's unbiased risk estimator (SURE), etc. seem to differ from one another and it is difficult to find the coherent mathematical structure. To address this, here we present a novel approach, called Noise2Score, which reveals a missing link in order to unite these seemingly different approaches. Specifically, we show that image denoising problems without clean images can be addressed by finding the mod…

2021-10-27cs.CVcs.LGeess.IV

ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithms

University of Iowa（爱荷华大学）

Image reconstruction using deep learning algorithms offers improved reconstruction quality and lower reconstruction time than classical compressed sensing and model-based algorithms. Unfortunately, clean and fully sampled ground-truth data to train the deep networks is often unavailable in several applications, restricting the applicability of the above methods. We introduce a novel metric termed the ENsemble Stein's Unbiased Risk Estimate (ENSURE) framework, which can be used to train deep image reconstruction algorithms without fully sampled and noise-free images. The proposed framework is t…

2022-12-02cs.CVcs.LGeess.IV