98%
921
2 minutes
20
Recent advances in deep-learning-based remote sensing image super-resolution (RSISR) have garnered significant attention. Conventional models typically perform upsampling at the end of the architecture, which reduces computational effort but leads to information loss and limits image quality. Moreover, the structural complexity and texture diversity of remote sensing images pose challenges in detail preservation. While transformer-based approaches improve global feature capture, they often introduce redundancy and overlook local details. To address these issues, we propose a novel progressive structure preservation and detail refinement super-resolution (PSPDR-SR) model, designed to enhance both structural integrity and fine details in RSISR. The model comprises two primary subnetworks: the structure-aware super-resolution (SaSR) subnetwork and the detail recovery and refinement (DR&R) subnetwork. To efficiently leverage multilayer and multiscale feature representations, we introduce coarse-to-fine dynamic information transmission (C2FDIT) and fine-to-coarse dynamic information transmission (F2CDIT) modules, which facilitate the extraction of richer details from low-resolution (LR) remote sensing images. These modules integrate transformers and convolutional long short-term memory (ConvLSTM) blocks to form dynamic information transmission modules (DITMs), enabling effective bidirectional feature transmission both horizontally and vertically. This method ensures comprehensive feature fusion, mitigates redundant information, and preserves essential extracted features within the deep network. Experimental results demonstrate that PSPDR-SR outperforms the state-of-the-art approaches on two benchmark datasets in both quantitative and qualitative evaluations, excelling in structure preservation and detail enhancement across various metrics, including SSIM, MS_SSIM, learned perceptual image patch similarity (LPIPS), deep image structure and texture similarity (DISTS), spatial correlation coefficient (SCC), and spectral angle mapper (SAM).
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1109/TNNLS.2025.3589209 | DOI Listing |
Environ Monit Assess
September 2025
Department of Environment and Life Science, KSKV Kachchh University, Bhuj, Gujarat, 370 001, India.
India's energy demand increased by 7.3% in 2023 compared to 2022 (5.6%), primarily met by coal-based thermal power plants (TPPs) that contribute significantly to greenhouse gas emissions.
View Article and Find Full Text PDFLight Sci Appl
September 2025
Laboratory of Quantum Information, University of Science and Technology of China, 230026, Hefei, China.
Quantum imaging with spatially entangled photons offers advantages such as enhanced spatial resolution, robustness against noise, and counterintuitive phenomena, while a biphoton spatial aberration generally degrades its performance. Biphoton aberration correction has been achieved by using classical beams to detect the aberration source or scanning the correction phase on biphotons if the source is unreachable. Here, a new method named position-correlated biphoton Shack-Hartmann wavefront sensing is introduced, where the phase pattern added on photon pairs with a strong position correlation is reconstructed from their position centroid distribution at the back focal plane of a microlens array.
View Article and Find Full Text PDFLight Sci Appl
September 2025
Key Lab of Environmental Optics & Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, 230031, Hefei, China.
Marine vessels play a vital role in the global economy; however, their negative impact on the marine atmospheric environment is a growing concern. Quantifying marine vessel emissions is an essential prerequisite for controlling these emissions and improving the marine atmospheric environment. Optical imaging remote sensing is a vital technique for quantifying marine vessel emissions.
View Article and Find Full Text PDFNat Commun
September 2025
State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing, 100875, China.
Rising atmospheric vapor pressure deficit (VPD)-a measure of atmospheric dryness, defined as the difference between saturated vapor pressure (SVP) and actual vapor pressure (AVP)-has been linked to increasing daily mean near-surface air temperatures since the 1980s. However, it remains unclear whether the faster increases in daily maximum temperature (T) relative to daily minimum temperature (T) have contributed to rising VPD. Here, we show that the faster rise in T compared with T over land has intensified VPD from 1980 to 2023.
View Article and Find Full Text PDFPlant Physiol Biochem
September 2025
Shanxi Normal University, Taiyuan, 030000, PR China.
Suaeda salsa(S.salsa) is a promising halophytic species for vegetation restoration in highly saline-alkali soils. Carboxylated single-walled carbon nanotubes (COOH-SWCNTs) have emerged as potential agents for modulating plant responses to abiotic stress.
View Article and Find Full Text PDF