1.武汉大学测绘遥感信息工程全国重点实验室,湖北 武汉,430079
2.中冶南方城市建设工程技术有限公司,湖北 武汉,430070
3.云南省卫星遥感技术应用工程中心,云南 昆明,650118
4.丹东东方测控技术股份有限公司,辽宁 丹东,118002
5.中国四维测绘技术有限公司,北京,100089
肖雄武,博士,副教授,现主要从事无人机实时测绘与SLAM技术、遥感影像超分等研究。E-mail:xwxiao@whu.edu.cn
姜瑞轩,硕士,现主要从事遥感影像超分、多模态遥感影像匹配研究。E-mail:1223119020@qq.com
修回:2026-09-03,
纸质出版:2026-10-05
移动端阅览
肖雄武,姜瑞轩,张之政,等.基于变化先验引导扩散模型的遥感图像超分辨率重建[J].测绘地理信息,2026,51(5):76-82
XIAO Xiongwu,JIANG Ruixuan,ZHANG Zhizheng,et al.Change-Prior Guided Diffusion for Super-Resolution Reconstruction of Remote Sensing Images[J].Journal of Geomatics,2026,51(5):76-82
肖雄武,姜瑞轩,张之政,等.基于变化先验引导扩散模型的遥感图像超分辨率重建[J].测绘地理信息,2026,51(5):76-82 DOI: 10.14188/j.2095-6045.20260468.
XIAO Xiongwu,JIANG Ruixuan,ZHANG Zhizheng,et al.Change-Prior Guided Diffusion for Super-Resolution Reconstruction of Remote Sensing Images[J].Journal of Geomatics,2026,51(5):76-82 DOI: 10.14188/j.2095-6045.20260468.
遥感图像超分辨率旨在从低分辨率影像中恢复高分辨率细节,对于城市监测、环境评估和灾害分析等遥感应用具有重要意义。近年来,扩散模型在图像生成与复原任务中取得了显著进展,但现有方法在复杂遥感场景中往往忽略变化区域信息,导致细节恢复不足或结构失真。针对这一问题,本文提出一种变化先验引导的扩散模型遥感图像超分辨率方法CPDiffSR。该方法通过引入变化先验信息对扩散模型的去噪与重建过程进行引导,从而增强变化区域的结构表达能力并保持未变化区域的纹理一致性。在HiUCD和MSSCD数据集上进行实验,LPIPS和DISTS分别达到的最优值为0.110 9和0.111 1。实验结果表明,CPDiffSR在性能上整体优于现有方法,并在视觉效果上生成更加清晰且结构一致的高分辨率遥感影像。实验结果验证了变化先验在扩散模型中的有效性,为复杂遥感场景下的图像超分辨率提供了一种新的思路。
The super-resolution of remote sensing images aims to recover high-resolution details from low-resolution images, which is of great significance for remote sensing applications such as urban monitoring, environmental assessment, and disaster analysis. In recent years, diffusion models have achieved remarkable progress in image generation and restoration tasks. However, existing methods often overlook change region information in complex remote sensing scenes, leading to insufficient detail restoration or structural distortion. To address this issue, this paper proposes a super-resolution method for remote sensing images based on the change-prior guided diffusion model, termed CPDiffSR. By introducing change-prior information to guide the denoising and reconstruction process of the diffusion model, this method enhances the structural representation of change regions while maintaining texture consistency in unchanged areas. Experiments conducted on the HiUCD and MSSCD datasets achieved optimal values of 0.110 9 and 0.111 1 for LPIPS and DISTS, respectively. The results demonstrate that CPDiffSR outperforms existing methods in overall performance and generates clearer, more structurally consistent high-resolution remote sensing images. These findings validate the effectiveness of change priors in diffusion models, offering a novel approach for image super-resolution in complex remote sensing scenarios.
Xin Liang , Li Zhipeng , Wang Sijian . Super-Resolution Research on Remote Sensing Images in the Megacity Based on Improved SRGAN [J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences , 2022 , V-3- 2022 : 603 - 609
Zhang Jizhou , Xu Tingfa , Li Jianan , et al . Single-Image Super-Resolution of Remote Sensing Images with Real-World Degradation Modeling [J]. Remote Sensing , 2022 , 14 ( 12 ): 2895
Liang Haotian , Zheng Change , Liu Xiaodong , et al . Super-Resolution Reconstruction of Remote Sensing Data Based on Multiple Satellite Sources for Forest Fire Smoke Segmentation [J]. Remote Sensing , 2023 , 15 ( 17 ): 4180
Rombach R , Blattmann A , Lorenz D , et al . High-Resolution Image Synthesis with Latent Diffusion Models [C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . June 18-24, 2022 , New Orleans, LA, USA . New York : IEEE Press , 2022 : 10 674-10 685
Ho J , Jain A , Abbeel P . Denoising Diffusion Probabilistic Models [PP/OL]. 2020: arXiv: 2006 .11239. https://arxiv.org/abs/2006.11239 https://arxiv.org/abs/2006.11239
Saharia C , Chan W , Chang Huiwen , et al . Palette: Image-to-Image Diffusion Models [C]// Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings . Vancouver BC Canada . ACM , 2022 : 1 - 10
Sohl-Dickstein J , Weiss E A , Maheswaranathan N , et al . Deep Unsupervised Learning Using Nonequilibrium Thermodynamics [PP/OL]. 2015: arXiv: 1503. 03585 . https://arxiv.org/abs/1503.03585 https://arxiv.org/abs/1503.03585
Tian Shiqi , Ma Ailong , Zheng Zhuo , et al . Hi-UCD: A Large-Scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery [PP/OL]. 2020: arXiv: 2011. 03247 . https://arxiv.org/abs/2011.03247 https://arxiv.org/abs/2011.03247
Guo Peixin , Yang Siyu , Zhang Hanchao , et al . HRMS-SCD: A High-Resolution Multi-scene Satellite Imagery Dataset for Comprehensive Land-Cover Semantic Change Detection [J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences , 2025 , X-G-2025: 323 - 331
Dong Chao , Loy C C , He Kaiming , et al . Image Super-Resolution Using Deep Convolutional Networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 38 ( 2 ): 295 - 307
Kim J , Lee J K , Lee K M . Accurate Image Super-Resolution Using very Deep Convolutional Networks [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . June 27-30, 2016 , Las Vegas, NV, USA . New York : IEEE Press , 2016 : 1 646-1 654
Lim B , Son S , Kim H , et al . Enhanced Deep Residual Networks for Single Image Super-Resolution [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . July 21-26, 2017 , Honolulu, HI, USA . New York : IEEE Press , 2017 : 1 132-1 140
Ledig C , Theis L , Huszár F , et al . Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . July 21-26, 2017 , Honolulu, HI . New York : IEEE Press , 2017 : 105 - 114
Wang Xintao , Yu Ke , Wu Shixiang , et al . ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks [C]// Computer Vision—ECCV 2018 Workshops . Cham : Springer , 2019 : 63 - 79
Liang Jingyun , Cao Jiezhang , Sun Guolei , et al . SwinIR: Image Restoration Using Swin Transformer [C]// 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) . October 11-17, 2021 , Montreal, BC, Canada . New York : IEEE Press , 2021 : 1 833-1 844
Yang Fuzhi , Yang Huan , Fu Jianlong , et al . Learning Texture Transformer Network for Image Super-Resolution [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . June 13-19, 2020 , Seattle, WA, USA . New York : IEEE Press , 2020 : 5 790-5 799
Saharia C , Ho J , Chan W , et al . Image Super-Resolution via Iterative Refinement [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 4 ): 4 713 - 4 726
Xiao Yi , Yuan Qiangqiang , Jiang Kui , et al . EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution [J]. IEEE Transactions on Geoscience and Remote Sensing , 2024 , 62 : 5601514
Luo Ziwei , Gustafsson F K , Zhao Zheng , et al . Image Restoration with Mean-Reverting Stochastic Differential Equations [PP/OL]. 2023: arXiv: 2301. 11699 . https://arxiv.org/abs/2301.11699 https://arxiv.org/abs/2301.11699
方宁 , 詹总谦 , 王鑫 . 一种用于视频超分辨率和去运动模糊联合处理的深度学习网络 [J]. 测绘地理信息 , 2024 , 49 ( 3 ): 91 - 95
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621