Image super-resolution (SR) technology can improve the resolution of images and provide clearer and more reliable remote sensing images of high quality to better serve the subsequent applications. However, when reconstructing high-frequency feature areas of remote sensing images, existing SR reconstruction methods are prone to artifacts that affect visual effects and make it difficult to generate real texture details. In order to address this issue, a texture-detail-enhanced dense generative adversarial network (TDEGAN) for remote sensing image SR is presented. The generator uses multi-level dense connections, residual connections, and Shuffle attention (SA) to improve the feature extraction ability. A PatchGAN-style discrimination network is designed to effectively perform local discrimination and helps the network generate rich, detailed features. To reduce the impact of artifacts, we introduce an artifact loss function, which is combined with the exponential moving average (EMA) technique to distinguish the artifacts generated from the actual texture details through local statistics, which can help the network reduce artifacts and generate more realistic texture details. Experiments show that TDEGAN can better restore the texture details of remote sensing images and achieves certain advantages in terms of evaluation indicators and visualization.

In recent years, great progress has been made in the field of super-resolution (SR) reconstruction based on deep learning techniques. Although image SR techniques show strong potential in image reconstruction, the effective application of these techniques to SR reconstruction of digital elevation models (DEMs) remains an important research challenge. The complexity and diversity of DEMs limits existing methods to capture subtle changes and features of the terrain, thus affecting the quality of reconstruction. To solve this problem, a DEM SR reconstruction network based on multi-path feature extraction and transformer feature enhancement is proposed in this paper. The network structure has three parts: feature extraction, image reconstruction, and feature enhancement. The feature extraction component consists of three feature extraction blocks, and each feature extraction block contains multiple multi-path feature residuals to enhance the interaction between spatial information and semantic information, so as to fully extract image features. In addition, the transformer feature enhancement module uses an encoder and decoder based design, leveraging the correlation between low- and high-dimensional features to further improve network performance. Through repeated testing and improvement, the model shows excellent performance in high-resolution DEM image reconstruction, and can generate more accurate DEMs. In terms of elevation and slope evaluation indexes, the model was 3.41% and 1.11% better compared with the existing reconstruction methods, which promotes the application of SR reconstruction technology in terrain data.