Effective variance attention-enhanced diffusion model for crop field aerial image super resolution

文献类型： 外文期刊

第一作者： Lu, Xiangyu

作者： Lu, Xiangyu;Zhang, Jianlin;Yang, Rui;Yang, Qina;Chen, Mengyuan;Liu, Fei;Xu, Hongxing;Guo, Jiawen;Wan, Pinjun

作者机构：

关键词： Super-resolution; Diffusion model; Variance attention; Aerial imagery; Super-resolution relative fidelity index

期刊名称：ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING （ 影响因子：12.2； 五年影响因子：13.7 ）

ISSN： 0924-2716

年卷期： 2024 年 218 卷

页码：

收录情况： SCI

摘要： Image super-resolution (SR) can significantly improve the resolution and quality of aerial imagery. Emerging diffusion models (DM) have shown superior image generation capabilities through multistep refinement. To explore their effectiveness on high-resolution cropland aerial imagery SR, we first built the CropSR dataset, which includes 321,992 samples for self-supervised SR training and two real-matched SR datasets from high-low altitude orthomosaics and fixed-point photography (CropSR-OR/FP) for testing. Inspired by the observed trend of decreasing image variance with higher flight altitude, we developed the Variance-Average-Spatial Attention (VASA). The VASA demonstrated effectiveness across various types of SR models, and we further developed the Efficient VASA-enhanced Diffusion Model (EVADM). To comprehensively and consistently evaluate the quality of SR models, we introduced the Super-resolution Relative Fidelity Index (SRFI), which considers both structural and perceptual similarity. On the x 2 and x 4 real SR datasets, EVADM reduced Fr & eacute;chet-Inception-Distance (FID) by 14.6 and 8.0, respectively, along with SRFI gains of 27 % and 6 % compared to the baselines. The superior generalization ability of EVADM was further validated using the open Agriculture-Vision dataset. Extensive downstream case studies have demonstrated the high practicality of our SR method, indicating a promising avenue for realistic aerial imagery enhancement and effective downstream applications. The code and dataset for testing are available at https://github.com/HobbitArmy/EVADM.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序