DSpix2pix: A New Dual-Style Controlled Reconstruction Network for Remote Sensing Image Super-Resolution
Source abstract
Abstract
Super-resolution reconstruction is a critical task in remote sensing image classification, and generative adversarial networks (GANs) have emerged as a dominant approach in this field. Traditional generative networks often produce low-quality images at resolutions like 256 × 256, and current research on single-image super-resolution typically focuses on resolution enhancement factors of two to four (2×–4×), which do not meet practical application demands. Building upon the framework of StyleGAN, this study introduces a dual-style controlled super-resolution reconstruction network referred to as DSpix2pix. It uses a fixed style vector (Style 1) from StyleGAN-v2, generated through its mapping network and applied to each layer in the generator. And an additional style vector (Style 2) is extracted from example images and injected into the decoder using AdIn, enhancing the balance of styles in the generated images. DSpix2pix is capable of generating high-quality, smoother, noise-reduced, and more realistic super-resolution remote sensing images at 512 × 512 and 1024 × 1024 resolutions. In terms of visual metrics such as RMSE, PSNR, SSIM, and LPIPS, it outperforms traditional super-resolution networks like SRGAN and UNIT, with RMSE consistently exceeding 10. The network excels in 2× and 4× super-resolution tasks, demonstrating potential for remote sensing image interpretation, and shows promising results in 8x super-resolution tasks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image and Signal Denoising Methods · Advanced Image Fusion Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Geosciences and Info-Physics, Central South University, Changsha 410017, China
Funding
National Natural Science Foundation of China · Institute of Land Resources Surveying and Mapping in Guangdong Province
References (38)
Show source-provided references
1. A review of remote sensing image super-resolution reconstruction methods based on deep learning
2. Landsat-8: Science and Product Vision for Terrestrial Global Change Research10.1016/j.rse.2014.02.001 ↗
3. Sentinel-2: ESA’s Optical High-Resolution Mission for Earth Observation10.1016/j.rse.2011.11.026 ↗
4. GMES Sentinel-1 mission10.1016/j.rse.2011.05.028 ↗
5. Methods and research progress in remote sensing image super-resolution processing
6. Research progress and perspectives on high/multispectral remote sensing image super-resolution fusion
7. Image super-resolution using deep convolutional networks10.1109/TPAMI.2015.2439281 ↗
8. Kim, J., Lee, J.K., and Lee, K.M. (2016, January 27–30). Accurate Image Super-Resolution Using Very Deep Convolutional Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.182 ↗
9. Zhang, Y., Tian, Y., Kong, Y., Zuo, W., and Zhang, L. (2018, January 18–22). Residual Dense Network for Image Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00262 ↗
10. Haris, M., Shakhnarovich, G., and Ukita, N. (2018, January 18–22). Deep Back-Projection Networks for Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00179 ↗
11. LGCNet: A local-to-global context-aware feature augmentation network for salient object detection10.1016/j.ins.2021.10.055 ↗
12. Xu, W., Xu, G., Wang, Y., Sun, X., Lin, D., and Wu, Y. (2018, January 22–27). High quality remote sensing image super-resolution using deep memory connected network. Proceedings of the IGARSS 2018—2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.10.1109/IGARSS.2018.8518855 ↗
13. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative Adversarial Nets. Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS’14), Montreal, QC, Canada.
14. A new deep generative network for unsupervised remote sensing single-image super-resolution10.1109/TGRS.2018.2843525 ↗
15. Edge-enhanced GAN for remote sensing image superresolution10.1109/TGRS.2019.2902431 ↗
16. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A.P., Tejani, A., Totz, J., and Wang, Z. (2017, January 21–26). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.19 ↗
17. Fleet, D., Pajdla, T., Scchiele, B., and Tuytelaars, T. (2014). Learning a Deep Convolutional Network for Image Super-Resolution. Computer Vision—ECCV 2014, Springer.10.1007/978-3-319-10578-9 ↗
18. Liu, M.-Y., Breuel, T., and Kautz, J. (2017, January 4–9). Unsupervised Image-to-Image Translation Networks. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
19. Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). Diverse image-to-image translation via disentangled representations. Computer Vision—ECCV 2018, Springer.
20. Deep Learning for Image Super-Resolution: A Survey10.1109/TPAMI.2020.2982166 ↗
21. Zhang, M., Sun, X., Zhu, Q., and Zheng, G. (2021, January 11–16). A Survey of Hyperspectral Image Super-Resolution Technology. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Brussels, Belgium.10.1109/IGARSS47720.2021.9554409 ↗
22. Sharma, A., Srivastava, B.P., and Shankar, P.N. (2023, January 18–19). Facial Image Super-Resolution with CNN A Review. Proceedings of the 2023 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India.10.1109/SCEECS57921.2023.10063110 ↗
23. Visible-light-driven photoswitching of aggregated-induced emission-active diarylethenes for super-resolution imaging10.1021/acsami.0c03122 ↗
24. Karras, T., Laine, S., and Aila, T. (2019, January 15–20). A style-based generator architecture for generative adversarial networks. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00453 ↗
25. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020, January 14–19). Analyzing and improving the image quality of StyleGAN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00813 ↗
26. Richardson, E., Alaluf, Y., Patashnik, O., Nitzan, Y., Azar, Y., Shapiro, S., and Cohen-Or, D. (2021, January 20–25). Encoding in style: A StyleGAN encoder for image-to-image translation. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00232 ↗
27. Yang, S., Jiang, L., Liu, Z., and Loy, C.C. (2022, January 18–24). Pastiche Master: Exemplar-based high-resolution portrait style transfer. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00754 ↗
28. Huang, X., and Belongie, S. (2017, January 22–29). Arbitrary style transfer in real-time with adaptive instance normalization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.167 ↗
29. Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
30. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
31. Wang, W., Huang, Y., Wang, Y., and Wang, L. (2014, January 23–28). Generalized autoencoder: A neural network framework for dimensionality reduction. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.10.1109/CVPRW.2014.79 ↗
32. A neural algorithm of artistic style10.1167/16.12.326 ↗
33. Navab, N., Hornegger, J., Wells, W., and Frangi, A. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer.10.1007/978-3-319-24571-3 ↗
34. Mirza, M., and Osindero, S. (2025, January 20). Conditional Generative Adversarial Nets. ArXiv 2014, abs/1411.1784. Available online: https://api.semanticscholar.org/CorpusID:12803511.
35. Zhu, Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.244 ↗
36. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
37. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–22). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
38. The Spectral Image Processing System (SIPS)—Interactive Visualization and Analysis of Imaging Spectrometer Data10.1016/0034-4257(93)90013-N ↗