Super-resolution methods have significantly contributed to the improvement of the spatial resolution of remote sensing images. The development of deep learning empowers novel methods to learn informative feature representation from massive low-resolution (LR) and high-resolution (HR) image pairs. Conventional remote sensing image super-resolution methods, however, may fail in large-scale (×8,×9) super-resolution tasks. Specifically, a larger scale factor corresponds to the less information in LR images, which is a considerable challenge to super-resolution. To address the issue, we propose a novel method for single remote sensing image super-resolution (SRSISR) based on stratified dense-sampling to effectively extract image features. Specifically, the proposed super-resolution dense-sampling residual attention network (SRDSRAN) combines dense-sampling and residual learning to improve multi-level feature fusion and gradient propagation, and employs local and global attentions to learn important features and long-range interdependence in the channel and spatial dimensions. Meanwhile, we also devise a discriminator model using local and global attentions, and with the loss function integrating L ₁ pixel loss, L ₁ perceptual loss, and relativistic adversarial loss to obtain the perceptually realistic images. Besides, we introduce a chain training to promote the performance and expedite the training process for large-scale super-resolution. Experimental results on UC Merced image and other multispectral data demonstrated that our SRDSRAN outperformed the current state-of-the-art methods quantitatively and in visual quality, and obtained a higher classification accuracy in scene classification, proving its potential for applications with other downstream tasks. We will open source our code at https://github.com/Meng-333/SRADSGAN.

Conventional deep learning-based methods for single remote sensing image super-resolution (SRSISR) have made remarkable progress. However, the super-resolution (SR) outputs of these methods are yet to become sufficiently satisfactory in visual quality. Recent Diffusion model-based generative deep learning models are capable to enhance the visual quality of output images, but this capability is limited due to their sampling efficiency. In this paper, we propose FastDiffSR, an SRSISR method based on a conditional Diffusion model. Specifically, we devise a novel sampling strategy to reduce the number of sampling steps required by the Diffusion model while ensuring the sampling quality. Meanwhile, the residual image is adopted to reduce computational costs, demonstrating that integrating channel attention and spatial attention begets a further improvement in the visual quality of output images. Compared to the state-of-the-art (SOTA) CNN-based, GAN-based, and Transformer-based SR methods, our FastDiffSR improves the learned perceptual image patch similarity (LPIPS) by 0.1-0.2 and achieves better visual results in some real-world scenes. Compared with existing Diffusion-based SR methods, our FastDiffSR achieves significant improvements in pixel-level evaluation metric peak signal-noise ratio (PSNR) while having smaller model parameters, and obtaining better SR results on Vaihingen data with faster inference time by 2.8-28 times, showing excellent generalization ability and time efficiency. Our code will be open source at https://github.com/Meng-333/FastDiffSR.

The spatial attention mechanism has been frequently employed for the semantic segmentation of remote sensing images, given its renowned capability to model long-range dependencies. As remote sensing images often exhibit intricate backgrounds, significant intraclass variability, and a foreground-background imbalance, spatial attention mechanism-based methods somehow tend to introduce an extensive amount of background context through intensive affinity operations, causing unsatisfactory segmentation outcomes. While several class-aware methods attempt to attenuate the interference of background context by generating class representations as representative features, they still encounter challenges related to independent correlation calculation and single-confidence scale class representations. We introduce a dual-domain optimized class-aware network designed to address these challenges. In the semantic domain, we use category confidence as a scaling criterion to derive class representations at multiple confidence scales, effectively modeling pixel-class relationships. In the spatial domain, we leverage pixel-class relationships and their consensus to enhance relevant correlations while suppressing erroneous ones. Experimental results on three datasets demonstrate that the proposed method surpasses previous state-of-the-art ones for remote sensing image segmentation. Code is available at https://github.com/xwmaxwma/rssegmentation .

Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.