Results 1 to 10 of about 1,040 (193)
IRE: Improved Image Super-Resolution Based on Real-ESRGAN
IEEE Access, 2023 Image super-resolution (SR) is a research field focusing on image degradation techniques. The High-order Deterioration Model (HDM) implemented in Real-ESRGAN has proven more effective in simulating the degradation of real-world images compared to ...
Chenyang Zhu, Yanping Zhu, Zhengwei Zhu
exaly +4 more sources
Remote SensingShip monitoring using Synthetic Aperture Radar (SAR) data faces significant challenges in detecting small vessels due to low spatial resolution and speckle noise.
Kohei Arai, Yu Morita, Hiroshi Okumura
exaly +4 more sources
Leveraging ESRGAN for High-Quality Retrieval of Low-Resolution Batik Pattern Datasets [PDF]
International Journal on Informatics VisualizationAs one of the world's cultural heritages in Indonesia, batik is one of the quite interesting research subjects, including in the realm of image retrieval.
Yufis Azhar +4 more
exaly +4 more sources
Research on Super-Resolution Reconstruction of Coarse Aggregate Particle Images for Earth–Rock Dam Construction Based on Real-ESRGAN [PDF]
SensorsThis paper investigates the super-resolution reconstruction technology of coarse granular particle images for embankment construction in earth/rock dams based on Real-ESRGAN, aiming to improve the quality of low-resolution particle images and enhance the
Shuangping Li +6 more
doaj +3 more sources
CA-ESRGAN: Super-Resolution Image Synthesis Using Channel Attention-Based ESRGAN
IEEE AccessAdvancements in deep learning algorithms and high-performance GPU computation have spurred extensive research in image processing. This study focuses on the synthesis of super-resolution images, a technique aimed at generating high-resolution images from
Jingan Liu, Naiwala P. Chandrasiri
doaj +4 more sources
Training ESRGAN with multi-scale attention U-Net discriminator [PDF]
Scientific ReportsIn this paper, we propose MSA-ESRGAN, a novel super-resolution model designed to enhance the perceptual quality of images. The key innovation of our approach lies in the integration of a multi-scale attention U-Net discriminator, which allows for more ...
Quan Chen, Hao Li, Gehao Lu
doaj +4 more sources
Model Specialization for the Use of ESRGAN on Satellite and Airborne Imagery [PDF]
Remote Sensing, 2021 Training a deep learning model requires highly variable data to permit reasonable generalization. If the variability in the data about to be processed is low, the interest in obtaining this generalization seems limited. Yet, it could prove interesting to specialize the model with respect to a particular theme.
Myriam Lemelin +2 more
exaly +4 more sources
ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network [PDF]
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020 ICASSP ...
Nathanael Carraz Rakotonirina
exaly +4 more sources
ESRGAN untuk Memperbesar Resolusi pada Citra Bangunan
Indonesian Journal of Computer Science, 2022 In the current era of technology, photos are an important existence for modern society where with photos we can get a lot of information. Quality photos must have a good resolution and level of sharpness, but sometimes the photos obtained are sometimes not satisfied, especially in the resolution section where there are some photos with low resolution ...
Agus Sulaeman +2 more
exaly +2 more sources
Super-Resolution of Medical Images Using Real ESRGAN
IEEE AccessRich details in an image are constantly vital for medical image analysis to detect a broad extent of medical ailments. The diagnosis will be best served if the image is accessible in high resolution and the small details are preserved.
Priyanka Nandal +3 more
doaj +2 more sources