.png){kind=icon}
返回
Efficient super resolution-based detail injection network for multispectral pan-sharpening
.png){kind=icon}
OA
AI
DOI：10.1080/10106049.2025.2537381.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Pan-sharpening is a panchromatic (PAN)-guided super-resolution (SR) process, focused on enhancing spatial resolution of low-resolution multi-spectral (LRMS). Existing SR-based pan-sharpening methods face two critical limitations: (1) lack of unified framework adaptable to both pan-sharpening and single image SR (SISR), and (2) inefficiencies in handling low-frequency feature redundancy in both spatial and frequency domain. Based on these, we model features in both spatial and frequency domain and propose a SR-based detail injection network (SDINet) for pan-sharpening. SDINet designs a global-local spatial extraction block (GSEB) for multi-scale feature extraction in spatial domain, accompanying a Sobel-based gated fusion block (SGFB) to non-linearly suppress low-frequency redundancy. Fourier frequency domain-based spatial detail injection block (FDIB) helps to extract supplement spatial information and to fluently convert SDINet for SISR task through input modification alone. Full-resolution and reduced-resolution experiments demonstrate the advantages of SDINet in both pan-sharpening and SISR tasks.
Keyword:
Convolutional neural network
multispectral pan-sharpening
spatial detail injection
single image super resolution
期刊
IF:
3.5
论文数:
2.4K
被引数:
6.9K
机构
引用论文
Ahmed N, Natarajan T, Rao K. 1974. Discrete cosine transform. IEEE Trans Comput. C-23(1):90–93. doi: 10.1109/T-C.1974.223784. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarAhmed N, Natarajan T, Rao K. 1974. Discrete cosine transform. IEEE Trans Comput. C-23(1):90–93. doi: 10.1109/T-C.1974.223784. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar.png)
IF0
PREAI
分享收藏Cai J, Huang B. 2021. Super-Resolution-Guided progressive pansharpening based on a deep convolutional neural network. IEEE Trans Geosci Remote Sensing. 59(6):5206–5220. doi: 10.1109/TGRS.2020.3015878. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarCai J, Huang B. 2021. 基于深度卷积神经网络的超分辨率引导渐进全色锐化. IEEE 地球科学与遥感学报. 59(6):5206–5220. doi: 10.1109/TGRS.2020.3015878. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏He X, Yan K, Li R, Xie C, Zhang J, Zhou M. 2024. Frequency-Adaptive Pan-Sharpening with Mixture of Experts. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), p. 2121–2129. doi: 10.1609/aaai.v38i3.27984. (Open in a new window)Google ScholarHe X, Yan K, Li R, Xie C, Zhang J, Zhou M. 2024. 频率自适应全色锐化方法研究：基于专家集成模型. 人工智能会议论文集，38(3)，第2121–2129页。doi: 10.1609/aaai.v38i3.27984. (在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Meng Q, Shi W, Li S, Zhang L. 2023. PANDIFF: a novel pansharpening method based on denoising diffusion probabilistic model. IEEE Trans Geosci Remote Sensing. 61:1–17. doi: 10.1109/TGRS.2023.3279864. (Open in a new window)Web of Science ®(Open in a new window)Google Scholar孟 Q, 石 W, 李 S, 张 L. 2023. PANDIFF：一种基于去噪扩散概率模型的全新全色锐化方法. IEEE 地球科学与遥感学报. 61:1–17. doi: 10.1109/TGRS.2023.3279864. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Vivone G, Alparone L, Chanussot J, Mura MD, Garzelli A, Licciardi GA, Restaino R, Wald L. 2015. A critical comparison among pansharpening algorithms. IEEE Trans Geosci Remote Sensing. 53(5):2565–2586. doi: 10.1109/TGRS.2014.2361734. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarVivone G, Alparone L, Chanussot J, Mura MD, Garzelli A, Licciardi GA, Restaino R, Wald L. 2015. 全色锐化算法的临界比较. IEEE Trans Geosci Remote Sensing. 53(5):2565–2586. doi: 10.1109/TGRS.2014.2361734. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Lim, B., S. Son, H. Kim, S. Nah, and K. M. Lee. 2017. “Enhanced Deep Residual Networks for Single Image Super-Resolution.” 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, 1132–1140. (Open in a new window)Google ScholarLim, B., S. Son, H. Kim, S. Nah, and K. M. Lee. 2017. “增强型深度残差网络用于单图像超分辨率重建。” 2017年IEEE计算机视觉与模式识别会议工作坊（CVPRW），美国夏威夷州火奴鲁鲁，第1132-1140页。（在新窗口中打开）Google Scholar
IF0
PREAI
分享收藏Li C, Li S, Liu X. 2025. Breaking through clouds: a hierarchical fusion network empowered by dual-domain cross-modality interactive attention for cloud-free image reconstruction. Information Fusion. 113:102649. doi: 10.1016/j.inffus.2024.102649. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarLi C, Li S, Liu X. 2025. 突破云层：一种由双域跨模态交互注意力赋能的分层融合网络用于无云图像重建。信息融合。113:102649. doi: 10.1016/j.inffus.2024.102649. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Masi G, Cozzolino D, Verdoliva L, Scarpa G. 2016. Pansharpening by convolutional neural networks. Remote Sensing. 8(7):594. doi: 10.3390/rs8070594. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarMasi G，Cozzolino D，Verdoliva L，Scarpa G. 2016. 基于卷积神经网络的泛锐化. 遥感. 8(7):594. doi: 10.3390/rs8070594. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Tan J, Huang J, Zheng N, Zhou M, Yan K, Hong D, Zhao F. 2024. Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion. Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 25922–25931. doi: 10.1109/CVPR52733.2024.02449. (Open in a new window)Google ScholarTan J, Huang J, Zheng N, Zhou M, Yan K, Hong D, Zhao F. 2024. 从分层视角重新审视全色和多光谱图像融合的空间-频率信息集成. 2024年IEEE/CVF计算机视觉与模式识别会议（CVPR）论文集, 25922–25931. doi: 10.1109/CVPR52733.2024.02449. (在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Li S, Tian Y, Xia H, Liu Q. 2022. Unmixing-Based PAN-Guided Fusion Network for Hyperspectral Imagery. IEEE Trans Geosci Remote Sensing. 60:1–17. 5522017 doi: 10.1109/TGRS.2022.3141765. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarLi S, Tian Y, Xia H, Liu Q. 2022. 基于解混的PAN引导融合网络用于高光谱图像。IEEE 传 感 地球科学与遥感汇刊. 60:1–17. 5522017 doi: 10.1109/TGRS.2022.3141765. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏
查看更多内容