首页/论文/1909.05305

arXiv 1909.053052019-09-11eess.IVcs.CV

Edge-Informed Single Image Super-Resolution

University of Ontario Institute of Technology（安大略理工大学）

Kamyar Nazeri, Harrish Thasarathan, Mehran Ebrahimi

英文摘要：

The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed approach to single image super-resolution (SISR). The SISR problem is reformulated as an image inpainting task. We use a two-stage inpainting model as a baseline for super-resolution and show its effectiveness for different scale factors (x2, x4, x8) compared to basic interpolation schemes. This model is trained using a joint optimization of image contents (texture and color) and structures (edges). Quantitative and qualitative comparisons are included and the proposed model is compared with current state-of-the-art techniques. We show that our method of decoupling structure and texture reconstruction improves the quality of the final reconstructed high-resolution image. Code and models available at: https://github.com/knazeri/edge-informed-sisr

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

基于物理信息集成表示的光场图像超分辨率

Physics-Informed Ensemble Representation for Light-Field Image Super-Resolution

Tianjin University（天津大学）

本文提出利用光场成像几何先验构建虚拟狭缝图像子空间，并学习所有LF子空间的集成表示，结合几何感知解码器EPIXformer，在空间和角度超分辨率任务中优于现有方法，尤其擅长处理不同视差。

2023-05-31cs.CVeess.IV

EPSR: Edge Profile Super resolution

Sungkyunkwan University（成均馆大学）；Hana Institute of Technology（哈娜理工学院）

In this paper, we propose Edge Profile Super Resolution(EPSR) method to preserve structure information and to restore texture. We make EPSR by stacking modified Fractal Residual Network(mFRN) structures hierarchically and repeatedly. mFRN is made up of lots of Residual Edge Profile Blocks(REPBs) consisting of three different modules such as Residual Efficient Channel Attention Block(RECAB) module, Edge Profile(EP) module, and Context Network(CN) module. RECAB produces more informative features with high frequency components. From the feature, EP module produce structure informed features by ge…

2021-05-12cs.CVeess.IV

COMISR: Compression-Informed Video Super-Resolution

Google Inc.（谷歌公司）

Most video super-resolution methods focus on restoring high-resolution video frames from low-resolution videos without taking into account compression. However, most videos on the web or mobile devices are compressed, and the compression can be severe when the bandwidth is limited. In this paper, we propose a new compression-informed video super-resolution model to restore high-resolution content without introducing artifacts caused by compression. The proposed model consists of three modules for video super-resolution: bi-directional recurrent warping, detail-preserving flow estimation, and L…

2021-10-12cs.CV

用于荧光显微镜跨模态超分辨率的物理信息深度学习模型

Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy

研究针对荧光显微镜跨模态超分辨率问题，提出将显微镜特定点扩散函数信息纳入训练目标的物理信息生成对抗网络，经实验验证该方法能提高模型结构保真度和物理合理性。

2026-07-24cs.CV

SIINR：用于临床质量扩散MRI数据集超分辨率及不确定性量化的结构信息隐式神经表示

SIINR: Structurally Informed Implicit Neural Representations for super-resolution with uncertainty quantification of clinical quality diffusion MRI datasets

Eindhoven University of Technology（埃因霍温理工大学）；University of South Carolina（南卡罗来纳大学）；Brigham and Women’s Hospital, Harvard Medical School（布莱根妇女医院，哈佛医学院）

针对临床dMRI数据集平面外分辨率低的问题，提出SIINR框架，利用监督3D U-net和自监督INR结合，实现超分辨率及不确定性量化，在多数据集和临床病例实验中表现优异，为临床dMRI增强及指标解释提供方法。

2026-07-23cs.CV

基于边缘信息对比度最大化的事件视觉奥秘

Secrets of Edge-Informed Contrast Maximization for Event-Based Vision

The University of Texas at Arlington（德克萨斯大学阿灵顿分校）

本文提出一种将对比度最大化从单模态扩展到双模态（事件与边缘）的混合方法，通过基于相关性的目标及多尺度多参考技术辅助优化，显著提升了边缘清晰度并在多个数据集上创下事件光流新基准。

2024-09-22cs.CVeess.IV

更多相关论文收起更多论文

结合四元数空间建模与动态流卷积的视觉感知型流场图像超分辨率

Vision-Informed Flow Image Super-Resolution with Quaternion Spatial Modeling and Dynamic Flow Convolution

Shanghai Jiao Tong University（上海交通大学）；Eastern Institute of Technology, Ningbo（宁波东方理工大学（暂名））

针对现有流场图像超分辨率方法忽略流场视觉特性导致性能受限的问题，提出结合四元数空间建模与动态流卷积的算法，在新数据集上取得了最优性能。

2024-01-29cs.CVcs.LGeess.IV

Generative Image Restoration and Super-Resolution using Physics-Informed Synthetic Data for Scanning Tunneling Microscopy

London Centre for Nanotechnology, University College London, London, United Kingdom（伦敦纳米技术中心，伦敦大学学院，英国）；Department of Electronic and Electrical Engineering, University College London, London, United Kingdom（电子与电气工程系，伦敦大学学院，英国）；University of Trieste, Trieste, Italy（特里斯特大学，意大利）

Scanning tunnelling microscopy (STM) enables atomic-resolution imaging and atom manipulation, but its utility is often limited by tip degradation and slow serial data acquisition. Fabrication adds another layer of complexity since the tip is often subjected to large voltages, which may alter the shape of its apex, requiring it to be conditioned. Here, we propose a machine learning (ML) approach for image repair and super-resolution to alleviate both challenges. Using a dataset of only 36 pristine experimental images of Si(001):H, we demonstrate that a physics-informed synthetic data generation…

2025-10-29cond-mat.mtrl-scics.CV

用于流行病学时间序列中状态变化超分辨率识别的动力学信息反卷积神经网络

Dynamics-informed deconvolutional neural networks for super-resolution identification of regime changes in epidemiological time series

Biofisika Institute (CSIC, UPV/EHU), University of the Basque Country (UPV/EHU)（Biofisika研究所（CSIC、UPV/EHU），巴斯克大学（UPV/EHU））；IKERBASQUE, Basque Foundation for Science（IKERBASQUE巴斯克科学基金会）；University of California（加利福尼亚大学）

提出一种无监督物理信息反卷积 CNN，将死亡记录逆向映射到发病率，实现单日分辨率的流行病学状态变化识别，并在 COVID-19 数据上以 0.93 天精度定位非药物干预。

2022-09-16cs.CVcs.LGq-bio.PE

BrainNormalizer：通过边缘引导控制网络从肿瘤MRI进行解剖学信息伪健康脑重建

BrainNormalizer: Anatomy-Informed Pseudo-Healthy Brain Reconstruction from Tumor MRI via Edge-Guided ControlNet

University of Pittsburgh（匹兹堡大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Cedars-Sinai Medical Center（西德萨斯医疗中心）；Mayo Clinic Arizona（梅奥诊所亚利桑那分部）

针对脑肿瘤致结构变形难区分肿瘤与解剖变异问题，提出BrainNormalizer框架，用两阶段训练学习解剖先验等，通过特定策略实现伪健康脑重建，实验表明其有优势。

2026-07-07cs.CVeess.IV

SDCL：面向半监督医学图像分割的学生差异信息校正学习

SDCL: Students Discrepancy-Informed Correction Learning for Semi-supervised Medical Image Segmentation

School of Computer Science and Technology, Southwest University of Science and Technology（西南科技大学计算机科学与技术学院）

针对半监督医学图像分割中伪标签偏差问题，提出SDCL框架，利用双学生分割差异引导自校正学习，并在多个数据集上超越现有SOTA方法。

2024-10-04cs.CVeess.IV

Dual camera snapshot hyperspectral imaging system via physics informed learning

Nanjing University of Science and Technology（南京理工大学）

We consider using the system's optical imaging process with convolutional neural networks (CNNs) to solve the snapshot hyperspectral imaging reconstruction problem, which uses a dual-camera system to capture the three-dimensional hyperspectral images (HSIs) in a compressed way. Various methods using CNNs have been developed in recent years to reconstruct HSIs, but most of the supervised deep learning methods aimed to fit a brute-force mapping relationship between the captured compressed image and standard HSIs. Thus, the learned mapping would be invalid when the observation data deviate from t…

2021-11-17cs.CVeess.IVphysics.optics

使用2D图像条件化3D扩散模型：通过En Face信息引导的超分辨率实现标准化OCT体数据

Conditioning 3D Diffusion Models with 2D Images: Towards Standardized OCT Volumes through En Face-Informed Super-Resolution

本文提出利用2D的en face SLO图像作为条件训练3D扩散模型，将高各向异性的OCT体数据标准化，在切片上采样8倍时优于传统插值和无条件扩散模型，提升了结构相干性并减少幻觉。

2024-10-13eess.IV

Physics-informed self-supervised deep learning reconstruction for accelerated first-pass perfusion cardiac MRI

Universidad de Valladolid（巴利亚多利德大学）；King’s College London（伦敦国王学院）；Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；Centre for Marine Sciences - CCMAR（海洋科学中心（CCMAR））

First-pass perfusion cardiac magnetic resonance (FPP-CMR) is becoming an essential non-invasive imaging method for detecting deficits of myocardial blood flow, allowing the assessment of coronary heart disease. Nevertheless, acquisitions suffer from relatively low spatial resolution and limited heart coverage. Compressed sensing (CS) methods have been proposed to accelerate FPP-CMR and achieve higher spatial resolution. However, the long reconstruction times have limited the widespread clinical use of CS in FPP-CMR. Deep learning techniques based on supervised learning have emerged as alternat…

2023-01-05cs.LGeess.IVphysics.med-ph