Upgan
An Unsupervised Generative Adversarial Network Based on U-Shaped Structure for Pansharpening
Bibliographic Data
| ID | 22033779 |
|---|---|
| Authors | Xin Jin (0000-0003-4590-5834, Yunnan University), Yuting Feng (0000-0001-7891-9824, Yunnan University), Qian Jiang (0000-0001-7131-0522, Yunnan University), Shengfa Miao (0000-0003-1210-1135, Yunnan University, corresponding author), Xing Chu (0000-0001-8654-7178, Yunnan University), Huangqimei Zheng (Yunnan University), Qianqian Wang (0000-0002-9558-9625, Yunnan University) |
| Year | 2024 |
| Volume | 13 |
| Issue | 7 |
| Pages | 222 |
| Publication date | 2024-06-26 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ISPRS International Journal of Geo-Information (JOURNAL) |
| Journal identifiers | ISSN: 2220-9964 • E-ISSN: 2220-9964 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/ijgi13070222 |
| OpenAlex | W4400047476 |
| Language | EN |
| References cited | 61 |
Pansharpening is the fusion of panchromatic images and multispectral images to obtain images with high spatial resolution and high spectral resolution, which have a wide range of applications. At present, methods based on deep learning can fit the nonlinear features of images and achieve excellent image quality; however, the images generated with supervised learning approaches lack real-world applicability. Therefore, in this study, we propose an unsupervised pansharpening method based on a generative adversarial network. Considering the fine tubular structures in remote sensing images, a dense connection attention module is designed based on dynamic snake convolution to recover the details of spatial information. In the stage of image fusion, the fusion of features in groups is applied through the cross-scale attention fusion module. Moreover, skip layers are implemented at different scales to integrate significant information, thus improving the objective index values and visual appearance. The loss function contains four constraints, allowing the model to be effectively trained without reference images. The experimental results demonstrate that the proposed method outperforms other widely accepted state-of-the-art methods on the QuickBird and WorldView2 data sets
Adversarial system · Deep learning · Generative adversarial network · Generative grammar · Machine learning · Advanced Image Fusion Techniques · Computer Science · Image and Signal Denoising Methods · Image Enhancement Techniques · Artificial Intelligence
Squeeze-and-Excitation Networks
Image quality assessment
A New Architecture of Densely Connected Convolutional Networks for Pan-Sharpening
Relief Supply-Demand Estimation Based on Social Media in Typhoon Disasters Using Deep Learning and a Spatial Information Diffusion Model
A Multi-Scale Water Extraction Convolutional Neural Network (MWEN) Method for GaoFen-1 Remote Sensing Images
Water Areas Segmentation from Remote Sensing Images Using a Separable Residual SegNet Network
| Citation velocity | historical |
|---|---|
| Highly cited | No |