Multiimage super-resolution (MISR), as one of the most promising directions in remote sensing, has become a needy technique in the satellite market. A sequence of images collected by satellites often has plenty of views and a long time span, so integrating multiple low-resolution views into a high-resolution image with details emerges as a challenging problem. However, most MISR methods based on deep learning cannot make full use of multiple images. Their fusion modules are incapable of adapting to an image sequence with weak temporal correlations well. To cope with these problems, we propose a novel end-to-end framework called TR-MISR. It consists of three parts: An encoder based on residual blocks, a transformer-based fusion module, and a decoder based on subpixel convolution. Specifically, by rearranging multiple feature maps into vectors, the fusion module can assign dynamic attention to the same area of different satellite images simultaneously. In addition, TR-MISR adopts an additional learnable embedding vector that fuses these vectors to restore the details to the greatest extent. TR-MISR has successfully applied the transformer to MISR tasks for the first time, notably reducing the difficulty of training the transformer by ignoring the spatial relations of image patches. Extensive experiments performed on the PROBA-V Kelvin dataset demonstrate the superiority of the proposed model that provides an effective method for transformers in other low-level vision tasks.

With the emergence of diffusion models, the image generation has experienced a significant advancement. In super-resolution tasks, diffusion models surpass generative adversarial network (GAN)-based methods in generating more realistic samples. However, these models come with significant costs: denoising networks rely on large U-Net, making them computationally intensive for high-resolution (HR) images, and the extensive sampling steps in diffusion models lead to prolonged inference time. This complexity limits their application in remote sensing, due to the high demand for high-resolution images in such scenarios. To address this, we propose a lightweight diffusion model (LWTDM), which simplifies the denoising network and efficiently incorporates conditional information using a cross-attention-based encoder–decoder architecture. Furthermore, LWTDM serves as the pioneering model that incorporates the accelerated sampling technique from denoising diffusion implicit models (DDIMs). This integration involves the meticulous selection of sampling steps, ensuring the quality of the generated images. The experiments confirm that LWTDM strikes a favorable balance between precision and perceptual quality, while its faster inference speed makes it suitable for diverse remote sensing scenarios with specific requirements. The source code is available at: https://github.com/Suanmd/LWTDM .

The advancements in image super-resolution technology have led to its widespread use in remote sensing applications. However, there is currently a lack of a general solution for the reconstruction of satellite images at arbitrary resolutions. The existing scale-arbitrary super-resolution methods are primarily predicated on learning either a discrete representation (DR) or a continuous representation (CR) of the image, with DR retaining the sensitivity to resolution and CR guaranteeing the generalization of the model. In this paper, we propose a novel image representation that combines the discrete and continuous representation, known as CDCR, which enables the extension of images to any desired resolution in a plug-and-play manner. CDCR consists of two components: a CR-based dense prediction that gathers more available information and a DR-based resolution-specific refinement that adjusts the predicted values of local pixels. Furthermore, we introduce a scale cumulative ascent (SCA) method, which enhances the performance of the dense prediction and improves the accuracy of the generated images at ultra-high magnifications. The efficacy and dependability of CDCR are substantiated by extensive experiments conducted on multiple remote sensing datasets, providing strong support for scenarios that require accurate images.