To achieve the goal of enhancing the resolution of Sentinel-2 satellite remote sensing images by a factor of four, this paper innovatively proposes a super-resolution model (S2SR) that combines VMamba and Transformer technologies. By skillfully introducing the Mixed Attention Block (MTB) and Cross Attention Block (CAMB), the model effectively integrates the channel attention mechanism with two-dimensional selective scanning technology. This design not only enhances the synergistic utilization of global and local features but also significantly improves the interaction capability of cross-window information through the overlapping cross-attention mechanism, effectively suppressing the common block effect issue in traditional super-resolution methods and thereby significantly enhancing the quality of reconstructed images. Experimental results demonstrate that on the SEN12MS standard dataset, the S2SR model exhibits superior performance compared to existing advanced methods in multiple no-reference image quality assessment metrics (such as NIQE, BRISQUE, PIQE). Especially when processing images with complex geographical features, the super-resolution images generated by the S2SR model exhibit clear edges and rich details, fully verifying the efficiency and practicality of the model.

Yunhe Li, Mei Yang, Tao Bian, Wenhui Xia and Haitao Wu. Super-Resolution Analysis of Remote Sensing Images Based on Cross-Attention. International Journal of Multimedia Computing (2024), Vol. 5, Issue 1: 43-53. https://doi.org/10.38007/IJMC.2024.050105.

[1] Phiri D, Simwanda M, Salekin S, et al. Sentinel-2 data for land cover/use mapping: A review[J]. Remote Sensing, 2020, 12(14): 2291.

[2] Li X, Chen J, Cui Z, et al. Single image super-resolution based on sparse representation with adaptive dictionary selection[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2016, 30(07): 1654006.

[3] Lei S, Shi Z. Hybrid-scale self-similarity exploitation for remote sensing image super-resolution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-10.

[4] Shao Z, Wang L, Wang Z, et al. Remote sensing image super-resolution using sparse representation and coupled sparse autoencoder[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(8): 2663-2674.

[5] Dong C, Loy C C, Tang X. Accelerating the super-resolution convolutional neural network[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14. Springer International Publishing, 2016: 391-407.

[6] Han K, Xiao A, Wu E, et al. Transformer in transformer[J]. Advances in neural information processing systems, 2021, 34: 15908-15919.

[7] Liu Z, Hu H, Lin Y, et al. Swin transformer v2: Scaling up capacity and resolution[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022: 12009-12019.

[8] Xu R, Yang S, Wang Y, et al. A survey on vision mamba: Models, applications and challenges[J]. arXiv preprint arXiv:2404.18861, 2024.

[9] Galar M, Sesma R, Ayala C, et al. Super-resolution of sentinel-2 images using convolutional neural networks and real ground truth data[J]. Remote Sensing, 2020, 12(18): 2941.

[10] Lin Z, Garg P, Banerjee A, et al. Revisiting rcan: Improved training for image super-resolution[J]. arXiv preprint arXiv:2201.11279, 2022.

[11] Salgueiro L, Marcello J, Vilaplana V. SEG-ESRGAN: A multi-task network for super-resolution and semantic segmentation of remote sensing images[J]. Remote Sensing, 2022, 14(22): 5862.

[12] Li Y, Wang Y, Li B, et al. Super-resolution of remote sensing images for× 4 resolution without reference images[J]. Electronics, 2022, 11(21): 3474.

[13] Wu L, Zhang X, Chen H, et al. Unsupervised quaternion model for blind colour image quality assessment[J]. Signal Processing, 2020, 176: 107708.

[14] Li H, Cao W, Li S, et al. Blind Image Quality Assessment Based on Natural Scene Statistics[J]. Journal of System Simulation, 2020, 28(12): 2903-2911.

[15] Ganesan P, Sathish B S, Vasanth K, et al. Color Image Quality Assessment Based on Full Reference and Blind Image Quality Measures[M]//Innovations in Electronics and Communication Engineering: Proceedings of the 8th ICIECE 2019. Singapore: Springer Singapore, 2020: 449-457.