Source-Adaptive Discriminative Kernels based Network for Remote Sensing Pansharpening
Siran Peng,Liang-Jian Deng,Jin-Fan Hu,Yu-Wei Zhuo +3 more
- 01 Jul 2022
pp 1283-1289
TL;DR: ADKNet as discussed by the authors proposes a convolutional neural network with source-adaptive discriminative kernels, which consist of spatial kernels generated from PAN images containing rich spatial details and spectral kernels from LR-MS images containing abundant spectral information.
read more
Abstract: For the pansharpening problem, previous convolutional neural networks (CNNs) mainly concatenate high-resolution panchromatic (PAN) images and low-resolution multispectral (LR-MS) images in their architectures, which ignores the distinctive attributes of different sources. In this paper, we propose a convolution network with source-adaptive discriminative kernels, called ADKNet, for the pansharpening task. Those kernels consist of spatial kernels generated from PAN images containing rich spatial details and spectral kernels generated from LR-MS images containing abundant spectral information. The kernel generating process is specially designed to extract information discriminately and effectively. Furthermore, the kernels are learned in a pixel-by-pixel manner to characterize different information in distinct areas. Extensive experimental results indicate that ADKNet outperforms current state-of-the-art (SOTA) pansharpening methods in both quantitative and qualitative assessments, in the meanwhile only with about 60,000 network parameters. Also, the proposed network is extended to the hyperspectral image super-resolution (HSISR) problem, still yields SOTA performance, proving the universality of our model. The code is available at http://github.com/liangjiandeng/ADKNet.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
PSRT: Pyramid Shuffle-and-Reshuffle Transformer for Multispectral and Hyperspectral Image Fusion
TL;DR: Zhang et al. as discussed by the authors proposed a pyramid Shuffle-and-Reshuffle Transformer (PSRT) for the task of multispectral and hyperspectral image fusion.
56
PSRT: Pyramid Shuffle-and-Reshuffle Transformer for Multispectral and Hyperspectral Image Fusion
TL;DR: Zhang et al. as discussed by the authors proposed a pyramid Shuffle-and-Reshuffle Transformer (PSRT) for multispectral and hyperspectral image fusion, considering the strong correlation among different patches in remote sensing images and complementary information among patches with high similarity.
47
Diffusion model with disentangled modulations for sharpening multispectral and hyperspectral images
Zihan Cao,Shiqi Cao,Liang-jian Deng,Xiao Wu,Junming Hou,Gemine Vivone +5 more
TL;DR: This paper introduces a supervised diffusion model with disentangled modulations for sharpening multispectral and hyperspectral images, outperforming state-of-the-art techniques through extensive experiments on pansharpening and multi-source image fusion benchmarks.
30
Multi-Scale Dual-Domain Guidance Network for Pan-sharpening
TL;DR: In this article , a multi-scale dual-domain guidance network (MSDDN) is proposed to exploit the distinguished information in both the spatial and frequency domains for pan-sharpening.
15
Bidomain Modeling Paradigm for Pansharpening
Junming Hou,Qi Cao,Ran Ran,Che Liu,Junling Li,Liang-jian Deng +5 more
- 26 Oct 2023
TL;DR: This work proposes a novel bidomain modeling paradigm for pansharpening problem (dubbed as BiMPan), which takes into both local spectral specificity and global spatial detail, and devise a novel Fourier global modeling module (FGMM), which is capable of embracing global information while benefiting the disentanglement of image degradation.
12
References
A universal image quality index
Zhou Wang,Alan C. Bovik +1 more
TL;DR: Although the new index is mathematically defined and no human visual system model is explicitly employed, experiments on various image distortion types indicate that it performs significantly better than the widely used distortion metric mean squared error.
6.2K
•Proceedings Article
Gaussian Processes for Regression
Christopher Williams,Carl Edward Rasmussen +1 more
- 27 Nov 1995
TL;DR: This paper investigates the use of Gaussian process priors over functions, which permit the predictive Bayesian analysis for fixed values of hyperparameters to be carried out exactly using matrix operations.
•Journal Article
Fusion of satellite images of different spatial resolutions: Assessing the quality of resulting images
TL;DR: In this article, the spectral properties of enhanced multispectral images with enhanced spatial resolution have been defined and a formal approach and some criteria to provide a quantitative assessment of the spectral quality of these products are defined.
1.5K
A Critical Comparison Among Pansharpening Algorithms
Gemine Vivone,Luciano Alparone,Jocelyn Chanussot,Mauro Dalla Mura,Andrea Garzelli,Giorgio Licciardi,Rocco Restaino,Lucien Wald +7 more
TL;DR: The authors attempt to fill the gap by providing a critical description and extensive comparisons of some of the main state-of-the-art pansharpening methods by offering a detailed comparison of their performances with respect to the different instruments.
1.2K
Pansharpening by Convolutional Neural Networks
TL;DR: A new pansharpening method is proposed, based on convolutional neural networks, which is largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.
1K