首页/论文/2009.03477

arXiv 2009.034772020-09-08cs.CVeess.IVmath.OC

A Residual Solver and Its Unfolding Neural Network for Total Variation Regularized Models

Yuanhao Gong

英文摘要：

This paper proposes to solve the Total Variation regularized models by finding the residual between the input and the unknown optimal solution. After analyzing a previous method, we developed a new iterative algorithm, named as Residual Solver, which implicitly solves the model in gradient domain. We theoretically prove the uniqueness of the gradient field in our algorithm. We further numerically confirm that the residual solver can reach the same global optimal solutions as the classical method on 500 natural images. Moreover, we unfold our iterative algorithm into a convolution neural network (named as Residual Solver Network). This network is unsupervised and can be considered as an "enhanced version" of our iterative algorithm. Finally, both the proposed algorithm and neural network are successfully applied on several problems to demonstrate their effectiveness and efficiency, including image smoothing, denoising, and biomedical image reconstruction. The proposed network is general and can be applied to solve other total variation regularized models.

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

USCTNet：一种用于物理一致高光谱图像重建的深度展开核范数求解器

USCTNet: A deep unfolding nuclear-norm optimization solver for physically consistent HSI reconstruction

Key Lab of Smart Agriculture Systems, Ministry of Education, China Agricultural University（中国农业大学教育部智能农业系统重点实验室）

本文提出USCTNet深度展开求解器，通过显式估计相机光谱灵敏度和光照保证物理一致性，并引入数据自适应低秩子空间SVT算子替代完整SVD，在RGB到高光谱重建任务中取得优于现有方法的精度。

2025-09-19cs.CV

Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing

Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Lab（鹏城实验室）

By integrating certain optimization solvers with deep neural network, deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS). However, there still exist several issues in existing DUNs: 1) For each iteration, a simple stacked convolutional network is usually adopted, which apparently limits the expressiveness of these models. 2) Once the training is completed, most hyperparameters of existing DUNs are fixed for any input content, which significantly weakens their adaptability. In this paper, by unfolding the Fast Iterative Shrinkage-Threshol…

2022-08-03cs.CVeess.IV

展开ADMM以增强高光谱图像的子空间聚类性能

Unfolding ADMM for Enhanced Subspace Clustering of Hyperspectral Images

Ghent University（根特大学）；China University of Geosciences（中国地质大学）

针对深度子空间聚类过拟合、可解释性差的问题，本文提出将ADMM迭代求解器展开的高光谱图像聚类架构，结合K近邻保留数据结构，在三个数据集上性能优于现有先进方法。

2024-06-21cs.CV

LCPNet：用于红外小目标检测的潜在一致近端展开网络

LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection

Department of Automation, Tsinghua University（清华大学自动化系）；Laboratory of Imaging Detection and Intelligent Perception, University of Electronic Science and Technology of China（电子科技大学成像探测与智能感知实验室）；School of Artificial Intelligence, Beijing Institute of Technology（北京理工大学人工智能学院）

针对红外小目标检测，提出LCPNet。通过在潜在空间展开并利用低秩先验，推导LCP求解器及引入共享优化内存，实现准确鲁棒检测，优于现有方法。

2026-10-16cs.AIcs.CV

Ada-LISTA: Learned Solvers Adaptive to Varying Models

Technion Institute of Technology（以色列理工学院）

Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance. Nevertheless, as opposed to non-learned solvers, these networks are trained on a certain dictionary, and therefore they are inapplicable for varying model scenarios. This work introduces an adaptive learned solver, termed Ada-LISTA, which receives pairs of signals and their corresponding dictionaries as inputs, and learns a universal architecture to serve them all. We prove that this scheme is guaranteed to solve s…

2020-02-19cs.CVcs.LGstat.ML

基于l0正则化稀疏编码的可解释网络用于多模态图像融合

l0-Regularized Sparse Coding-based Interpretable Network for Multi-Modal Image Fusion

Department of EE, IIT Kharagpur, India（印度IIT Kharagpur电子工程系）；Rekhi Centre of Excellence for the Science of Happiness, IIT Kharagpur, India（印度IIT Kharagpur幸福科学卓越中心）；Department of E&ECE, IIT Kharagpur, India（印度IIT Kharagpur电子工程与电子学系）

本文提出基于l0正则化稀疏编码的可解释网络FNet，用于多模态图像融合，通过分离独特和共同特征提升融合质量并增强下游任务性能。

2025-12-11cs.CV

更多相关论文收起更多论文

AXS-Net：基于光谱基元分解与结构化噪声细化的高光谱图像去噪可解释深度展开

AXS-Net: Interpretable Deep Unfolding for Hyperspectral Image Denoising via Spectral Basis Unmixing and Structured Noise Refinement

Xiangtan University（湘潭大学）

AXS-Net 通过将高光谱去噪建模为光谱分解与结构化噪声分离的优化问题并展开为深度网络，实现了可解释去噪，在多个数据集上表现优异。

2026-09-09cs.CV

UnfoldIR：重新思考光照退化图像复原中的深度展开网络

UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration

Duke University（杜克大学）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）

本文提出 UnfoldIR，通过面向光照退化的复原模型、VSS 模块与阶段间一致性损失改进深度展开网络，并在 5 项任务和 3 个下游问题上验证有效性。

2025-05-10cs.CV

深度展开网络用于图像压缩感知：基于内容自适应梯度更新与变形不变非局部建模

Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling

Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）

提出DUN-CSNet深度展开网络，通过内容自适应梯度更新和变形不变非局部建模解决图像压缩感知中超参数内容无关与上下文感知不足的问题，大幅超越现有方法。

2023-10-16cs.CVcs.MM

用于图像超分辨率的感知正则化扩散模型

Perceptually Regularized Diffusion Model for Image Super-Resolution

University of North Carolina（北卡罗来纳大学）；Texas Tech University（德克萨斯理工大学）；Case Western Reserve University（凯斯西储大学）；University of Houston（休斯顿大学）；University of Kentucky（肯塔基大学）

针对扩散模型图像超分辨率的像素域噪声预测损失易致过平滑的问题，提出感知正则化扩散框架，实验证实其可提升感知质量与失真度量表现。

2026-09-03cs.CVcs.LGeess.IV

Fast and Regularized Reconstruction of Building Façades from Street-View Images using Binary Integer Programming

China Railway First Survey and Design Institute Co. Ltd.（中铁第一勘察设计院集团有限公司）；Southwest Jiaotong University（西南交通大学）

Regularized arrangement of primitives on building façades to aligned locations and consistent sizes is important towards structured reconstruction of urban environment. Mixed integer linear programing was used to solve the problem, however, it is extreamly time consuming even for state-of-the-art commercial solvers. Aiming to alleviate this issue, we cast the problem into binary integer programming, which omits the requirements for real value parameters and is more efficient to be solved . Firstly, the bounding boxes of the primitives are detected using the YOLOv3 architecture in real-time. Se…

2020-04-22cs.CV

RU-Net: Regularized Unrolling Network for Scene Graph Generation

South China University of Technology（华南理工大学）；Pazhou Lab（琶洲实验室）；The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）

Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects. Existing SGG methods usually suffer from several issues, including 1) ambiguous object representations, as graph neural network-based message passing (GMP) modules are typically sensitive to spurious inter-node correlations, and 2) low diversity in relationship predictions due to severe class imbalance and a large number of missing annotations. To address both problems, in this paper, we propose a regularized unrolling network (RU-Net). We first study the relation between GMP and gra…

2022-05-03cs.CV

一种用于非凸 AI 增强医学图像处理的增量算法

An incremental algorithm for non-convex AI-enhanced medical image processing

Dept of Political and Social Sciences University of Bologna（政治与社会科学系伯洛尼亚大学）

本文提出 incDG 混合框架，融合深度学习初始化与非凸增量变分优化，以逼近 $\ell_0$ 最优解，并在医学图像去模糊和断层重建中展现出优于传统及深度学习方法的准确性、稳定性和无真值训练实用性。

2025-05-13cs.CVcs.NAmath.NA

An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation

University at Buffalo, The State University of New York（纽约州立大学布法罗分校）

Many segmentation tasks for biomedical images can be modeled as the minimization of an energy function and solved by a class of max-flow and min-cut optimization algorithms. However, the segmentation accuracy is sensitive to the contrasting of semantic features of different segmenting objects, as the traditional energy function usually uses hand-crafted features in their energy functions. To address these limitations, we propose to incorporate end-to-end trainable neural network features into the energy functions. Our deep neural network features are extracted from the down-sampling and up-sam…

2021-09-01cs.CVcs.LG