中文
相关论文

相关论文: A comparative study of paired versus unpaired deep…

200 篇论文

Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic…

计算机视觉与模式识别 · 计算机科学 2019-04-02 Jianrui Cai , Hui Zeng , Hongwei Yong , Zisheng Cao , Lei Zhang

Images play a vital role in understanding data through visual representation. It gives a clear representation of the object in context. But if this image is not clear it might not be of much use. Thus, the topic of Image Super Resolution…

计算机视觉与模式识别 · 计算机科学 2021-10-28 Umashankar Kumaravelan , Nivedita M

Detecting changed regions in paired satellite images plays a key role in many remote sensing applications. The evolution of recent techniques could provide satellite images with very high spatial resolution (VHR) but made it challenging to…

图像与视频处理 · 电气工程与系统科学 2021-12-08 Caijun Ren , Xiangyu Wang , Jian Gao , Huanhuan Chen

In recent years, much research has been conducted on image super-resolution (SR). To the best of our knowledge, however, few SR methods were concerned with compressed images. The SR of compressed images is a challenging task due to the…

计算机视觉与模式识别 · 计算机科学 2017-09-20 Honggang Chen , Xiaohai He , Chao Ren , Linbo Qing , Qizhi Teng

Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques. As a result, the tasks are usually approached by unpaired techniques based on Generative Adversarial…

图像与视频处理 · 电气工程与系统科学 2025-07-09 Milena Gazdieva , Petr Mokrov , Litu Rout , Alexander Korotin , Andrey Kravchenko , Alexander Filippov , Evgeny Burnaev

We develop a procedure for substantially improving the quality of segmented 3D micro-Computed Tomography (micro-CT) images of rocks with a Machine Learning (ML) Generative Model. The proposed model enhances the resolution eightfold (8x) and…

图像与视频处理 · 电气工程与系统科学 2025-01-14 Evgeny Ugolkov , Xupeng He , Hyung Kwak , Hussein Hoteit

Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than synthetic SR tasks. This is critical for applications like…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Chaowei Fang , Bolin Fu , De Cheng , Lechao Cheng , Guanbin Li

Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk. However, the widely reported supervised LDCT denoising networks require a training set of paired images, which is…

机器学习 · 计算机科学 2023-02-09 Yuhui Ruan , Qiao Yuan , Chuang Niu , Chen Li , Yudong Yao , Ge Wang , Yueyang Teng

Due to the limitations of sensors, the transmission medium and the intrinsic properties of ultrasound, the quality of ultrasound imaging is always not ideal, especially its low spatial resolution. To remedy this situation, deep learning…

图像与视频处理 · 电气工程与系统科学 2020-12-29 Heng Liu , Jianyong Liu , Tao Tao , Shudong Hou , Jungong Han

Recent advances in deep learning, particularly neural networks, have significantly impacted a wide range of fields, including the automatic enhancement of underwater images. This paper presents a deep learning-based approach to improving…

计算机视觉与模式识别 · 计算机科学 2025-07-09 Jose M. Montero , Jose-Luis Lisani

Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-world captured datasets, there exists semantic mismatch between…

计算机视觉与模式识别 · 计算机科学 2023-04-27 Ganning Zhao , Tingwei Shen , Suya You , C. -C. Jay Kuo

Micro-CT scanning of rocks significantly enhances our understanding of pore-scale physics in porous media. With advancements in pore-scale simulation methods, such as pore network models, it is now possible to accurately simulate multiphase…

图像与视频处理 · 电气工程与系统科学 2024-09-19 Zihan Ren , Sanjay Srinivasan

Computed Tomography (CT) imaging technique is widely used in geological exploration, medical diagnosis and other fields. In practice, however, the resolution of CT image is usually limited by scanning devices and great expense. Super…

计算机视觉与模式识别 · 计算机科学 2020-01-29 Yukai Wang , Qizhi Teng , Xiaohai He , Junxi Feng , Tingrong Zhang

The deep learning technique was used to increase the performance of single image super-resolution (SISR). However, most existing CNN-based SISR approaches primarily focus on establishing deeper or larger networks to extract more significant…

计算机视觉与模式识别 · 计算机科学 2022-12-29 Huipeng Zheng , Lukman Hakim , Takio Kurita , Junichi Miyao

High-quality magnetic resonance (MR) image, i.e., with near isotropic voxel spacing, is desirable in various scenarios of medical image analysis. However, many MR acquisitions use large inter-slice spacing in clinical practice. In this…

图像与视频处理 · 电气工程与系统科学 2021-08-18 Kai Xuan , Liping Si , Lichi Zhang , Zhong Xue , Yining Jiao , Weiwu Yao , Dinggang Shen , Dijia Wu , Qian Wang

We introduce a new learning strategy for image enhancement by recurrently training the same simple superresolution (SR) network multiple times. After initially training an SR network by using pairs of a corrupted low resolution (LR) image…

图像与视频处理 · 电气工程与系统科学 2019-07-29 Saem Park , Nojun Kwak

The capabilities of super-resolution reconstruction (SRR)---techniques for enhancing image spatial resolution---have been recently improved significantly by the use of deep convolutional neural networks. Commonly, such networks are learned…

计算机视觉与模式识别 · 计算机科学 2019-06-18 Michal Kawulok , Szymon Piechaczek , Krzysztof Hrynczenko , Pawel Benecki , Daniel Kostrzewa , Jakub Nalepa

Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the…

计算机视觉与模式识别 · 计算机科学 2020-04-27 Feng Li , Runming Cong , Huihui Bai , Yifan He

Learning single image deraining (SID) networks from an unpaired set of clean and rainy images is practical and valuable as acquiring paired real-world data is almost infeasible. However, without the paired data as the supervision, learning…

计算机视觉与模式识别 · 计算机科学 2022-03-25 Xiang Chen , Jinshan Pan , Kui Jiang , Yufeng Li , Yufeng Huang , Caihua Kong , Longgang Dai , Zhentao Fan

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…

计算机视觉与模式识别 · 计算机科学 2018-11-20 Bolin Liu , Xiao Shu , Xiaolin Wu