Enhancing Remote Sensing Image Super-Resolution with Efficient Hybrid Conditional Diffusion Model

Abstract

Recently, optical remote-sensing images have been widely applied in fields such as environmental monitoring and land cover classification. However, due to limitations in imaging equipment and other factors, low-resolution images that are unfavorable for image analysis are often obtained. Although existing image super-resolution algorithms can enhance image resolution, these algorithms are not specifically designed for the characteristics of remote-sensing images and cannot effectively recover high-resolution images. Therefore, this paper proposes a novel remote-sensing image super-resolution algorithm based on an efficient hybrid conditional diffusion model (EHC-DMSR). The algorithm applies the theory of diffusion models to remote-sensing image super-resolution. Firstly, the comprehensive features of low-resolution images are extracted through a transformer network and CNN to serve as conditions for guiding image generation. Furthermore, to constrain the diffusion model and generate more high-frequency information, a Fourier high-frequency spatial constraint is proposed to emphasize high-frequency spatial loss and optimize the reverse diffusion direction. To address the time-consuming issue of the diffusion model during the reverse diffusion process, a feature-distillation-based method is proposed to reduce the computational load of U-Net, thereby shortening the inference time without affecting the super-resolution performance. Extensive experiments on multiple test datasets demonstrated that our proposed algorithm not only achieves excellent results in quantitative evaluation metrics but also generates sharper super-resolved images with rich detailed information.

PixRevive: Latent Feature Diffusion Model for Compressed Video Quality Enhancement

“…To better enhance the image restoration capability of diffusion models, existing works [ 43 , 44 ] incorporate latent features from conditional neural networks into training diffusion models. Specifically, the method extracts integrated features from low-resolution images through a neural network for conditioning to guide image generation.…”

“…If they are directly linearly or nonlinearly combined, the desired performance results cannot be obtained. The existing methods, such as those in [ 43 , 52 ], that fuse convolutional neural networks with diffusion models directly fuse features from the two domains with gaps, which will inevitably lead to image distortions and detail losses. Therefore, how to organically and concisely achieve the fusion of the two has become a universally recognized challenge.…”

AutoSR4EO: An AutoML Approach to Super-Resolution for Earth Observation Images

“…Recently, SR approaches using diffusion techniques have been proposed. For instance, Han et al [50] used diffusion to create detailed super-resolved images and used feature distillation to reduce inference time. Wu et al [51] used diffusion together with contrastive learning to estimate the degradation kernels of images, without making assumptions about the kernels.…”

The Crack Diffusion Model: An Innovative Diffusion-Based Method for Pavement Crack Detection

“…However, currently, diffusion models are primarily used in the field of image generation. Unlike discriminative models, which can easily compute the correlation between predicted results and ground truth, there are only a few generative tasks that have welldefined ground truth, such as image super-resolution [23]. Currently, there is no research on incorporating the learning capability of diffusion models into crack detection.…”