Exploiting Digital Surface Models for Inferring Super-Resolution for Remotely Sensed Images

Karatsiolis, Savvas; Padubidri, Chirag; Kamilaris, Andreas

doi:10.1109/tgrs.2022.3209340

Cited by 4 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…𝐿 𝑐𝑜𝑛𝑡𝑒𝑛𝑡 calculates the 1-norm elevation distance between the SR DSM and the HR DSM and it can optimize the elevation accuracy of DSM at the pixel-level in Eq. (5).…”

Section: ) Content Lossmentioning

confidence: 99%

“…OPOGRAPHIC data play a crucial role in characterizing the elevation and location of Earth's surface and they are fundamental inputs for a wide range of geoscience applications [1][2][3][4][5][6]. Digital terrain model (DTM), digital elevation model (DEM) and digital surface model (DSM) are three types of commonly used topographic data [3,7].…”

Section: Introductionmentioning

confidence: 99%

“…Typically, there are two main ways to obtain highresolution DSM datasets. The first way is to improve the resolution of surveying equipment (e.g., light detection and ranging laser scanner and stereo image pairs from aerial camera), which includes the utilization of more sophisticated sensors, instruments or techniques capable of capturing topographic data with higher resolution [2,5,29]. However, this way often requires a significant investment in labor, materials, and technical expertise.…”

Section: Introductionmentioning

confidence: 99%

“…The second way is to use the super-resolution (SR) technique to increase the spatial resolution of DSM datasets, particularly those based on machine learning [9,24,25,27,28,[30][31][32]. SR refers to the process of enhancing the resolution of an image or dataset beyond its original level to achieve a more detailed representation of underlying features [5,25,[33][34][35][36][37][38]. With the rapid development of deep learning, many image SR algorithms have been proposed by leveraging the advantages of convolutional neural networks (CNN) and generative adversarial networks (GAN), such as super-resolution convolutional neural network (SRCNN) [39], super-resolution generative adversarial networks (SRGAN) [40], and enhanced super-resolution generative adversarial networks (ESRGAN) [41].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Digital Surface Model Super-Resolution by Integrating High-Resolution Remote Sensing Imagery Using Generative Adversarial Networks

Sun,

Chen,

Huang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Digital Surface Model (DSM) is the fundamental data in various geoscience applications, such as city 3D modeling and urban environment analysis. The freely available DSM often suffers from limited spatial resolution. Super-resolution (SR) is a promising technique to increase the spatial resolution of DSM. However, most existing SR models struggle to reconstruct spatial details such as buildings, valleys, and ridges. This paper proposes a novel DSM super-resolution (DSMSR) model that integrates high-resolution remote sensing imagery using generative adversarial networks. The generator in DSMSR contains three modules. The first DSM feature extraction module uses the residual-in-residual dense block (RRDB) to extract features from low-resolution DSM. The second multiscale attention feature extraction module employs the pyramid convolutional residual dense (PCRD) blocks to capture spatial details of ground objects at multiple scales from remote sensing imagery. The third DSM reconstruction module uses a squeeze-and-excitation (SE) block to fuse the extracted features from low-resolution DSM and highresolution remote sensing imagery for generating SR DSM. The discriminator of DSMSR uses the relativistic average discriminator (RaD) for adversarial learning. The slope loss is further introduced to ensure the accurate representation of topographic features. We evaluate DSMSR on four different terrain regions in the UK to downscale the 30-m AW3D30 DSM to 5-m DSM. The experimental results indicate that DSMSR outperforms traditional interpolation algorithms and four existing deep learning-based SR models. The DSMSR restores more spatial detail of topographic features and generates more accurate image quality, elevation and terrain metrics.

show abstract

Section: ) Content Lossmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Digital Surface Model Super-Resolution by Integrating High-Resolution Remote Sensing Imagery Using Generative Adversarial Networks

Sun,

Chen,

Huang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…SISR is a challenging task that aims to reconstruct an HR image from an LR image. This task has many applications in various fields, such as satellite imagery [29], monitoring equipment [30], remote sensing images [31], medical imaging [32], and so on. However, SISR is an ill-posed problem because one LR image can correspond to multiple HR images.…”

Section: Single-scale Deep Back-projection Networkmentioning

confidence: 99%

A Multi-Scale Deep Back-Projection Backbone for Face Super-Resolution with Diffusion Models

2023

View full text Add to dashboard Cite

Face verification and recognition are important tasks that have made great progress in recent years. However, recognizing low-resolution faces from small images is still a difficult problem. In this paper, we advocate using diffusion models (DMs) to enhance face resolution and improve their quality for various downstream applications. Most existing DMs for super-resolution use U-Net as their backbone network, which only exploits multi-scale features along the spatial dimension. These approaches result in a slow convergence of corresponding DMs and the inability to capture complex details and fine textures. To address this issue, we propose a novel conditional generative model based on DMs called BPSR3, which replaces the U-Net in super-resolution via repeated refinement (SR3) with a multi-scale deep back-projection network structure. BPSR3 can extract richer features not only in depth but also in breadth. This helps to effectively refine the image quality at different scales. The experimental results on facial datasets show that BPSR3 significantly improved both convergence speed and reconstruction performance. BPSR3 has about 1/4 of the parameters of SR3 but achieves a 50.1% improvement in PSNR, a 19.8% improvement in SSIM, and a 15.4% reduction in FID. Our contribution lies in achieving less time and space consumption and better reconstruction results. In addition, we propose an idea of enhancing the performance of DMs by replacing the U-Net with a better network.

show abstract

Remote Sensing Image Super-Resolution using Deep Learning

Rajeshwari,

Priya,

Pooja

et al. 2024

2024 IEEE Space, Aerospace and Defence Conference (SPACE)

View full text Add to dashboard Cite

Exploiting Digital Surface Models for Inferring Super-Resolution for Remotely Sensed Images

Cited by 4 publications

References 41 publications

Digital Surface Model Super-Resolution by Integrating High-Resolution Remote Sensing Imagery Using Generative Adversarial Networks

Digital Surface Model Super-Resolution by Integrating High-Resolution Remote Sensing Imagery Using Generative Adversarial Networks

A Multi-Scale Deep Back-Projection Backbone for Face Super-Resolution with Diffusion Models

Remote Sensing Image Super-Resolution using Deep Learning

Contact Info

Product

Resources

About