TY - JOUR
T1 - Comparative Study of Stable Diffusion-Based Super-Resolution Methods for Remote Sensing Imagery
AU - Lu, Yiran
AU - He, Hongjie
AU - Zhu, Fei
AU - Li, Jonathan
N1 - Publisher Copyright:
© 2026 Yiran Lu et al.
PY - 2026/7/30
Y1 - 2026/7/30
N2 - Remote sensing image super-resolution aims to recover fine structural and textural details from degraded low-resolution observations. However, conventional methods and early deep learning models often produce over-smoothed results and struggle to reconstruct realistic high-frequency content. Stable Diffusion-based (SD-based) methods offer a promising alternative by using strong generative priors to synthesize more natural, detail-rich super-resolved images. Although many SD-based super-resolution methods have been proposed in computer vision, their use in remote sensing imagery remains limited, and systematic comparative evaluation in this domain is still lacking, leaving insufficient empirical guidance for method development. Therefore, this paper compares four representative SD-based super-resolution methods, namely Stable Super-Resolution (StableSR), Semantics-Aware Super-Resolution (SeeSR), Different Blind Image Restoration (DiffBIR), and Pixel-Aware Stable Diffusion (PASD), on the WHU-Mix remote sensing dataset. The evaluation uses seven metrics: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), Frechet Inception Distance (FID), CLIP Image Quality Assessment (CLIP-IQA), Multi-Scale Image Quality Transformer (MUSIQ), and Multi-Dimension Attention Network for No-Reference Image Quality Assessment (MANIQA). Quantitative results show that StableSR achieves the highest PSNR of 23.16 dB, PASD obtains the best SSIM of 0.81 and lowest LPIPS of 0.45, SeeSR achieves the best MUSIQ of 64.57 and MANIQA of 0.46, and DiffBIR achieves the best FID of 110.58 and CLIP-IQA of 0.68 but with weaker full-reference fidelity. These findings indicate that current SD-based methods favor different aspects, including fidelity preservation, perceptual quality, and generative realism, and should be selected according to the target remote sensing application.
AB - Remote sensing image super-resolution aims to recover fine structural and textural details from degraded low-resolution observations. However, conventional methods and early deep learning models often produce over-smoothed results and struggle to reconstruct realistic high-frequency content. Stable Diffusion-based (SD-based) methods offer a promising alternative by using strong generative priors to synthesize more natural, detail-rich super-resolved images. Although many SD-based super-resolution methods have been proposed in computer vision, their use in remote sensing imagery remains limited, and systematic comparative evaluation in this domain is still lacking, leaving insufficient empirical guidance for method development. Therefore, this paper compares four representative SD-based super-resolution methods, namely Stable Super-Resolution (StableSR), Semantics-Aware Super-Resolution (SeeSR), Different Blind Image Restoration (DiffBIR), and Pixel-Aware Stable Diffusion (PASD), on the WHU-Mix remote sensing dataset. The evaluation uses seven metrics: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), Frechet Inception Distance (FID), CLIP Image Quality Assessment (CLIP-IQA), Multi-Scale Image Quality Transformer (MUSIQ), and Multi-Dimension Attention Network for No-Reference Image Quality Assessment (MANIQA). Quantitative results show that StableSR achieves the highest PSNR of 23.16 dB, PASD obtains the best SSIM of 0.81 and lowest LPIPS of 0.45, SeeSR achieves the best MUSIQ of 64.57 and MANIQA of 0.46, and DiffBIR achieves the best FID of 110.58 and CLIP-IQA of 0.68 but with weaker full-reference fidelity. These findings indicate that current SD-based methods favor different aspects, including fidelity preservation, perceptual quality, and generative realism, and should be selected according to the target remote sensing application.
KW - Comparative Study
KW - Diffusion-based Super-Resolution
KW - Remote Sensing
KW - Stable Diffusion
KW - Super-resolution
UR - https://www.scopus.com/pages/publications/105047275037
U2 - 10.5194/isprs-archives-XLIX-B3-2026-1435-2026
DO - 10.5194/isprs-archives-XLIX-B3-2026-1435-2026
M3 - 会议文章
AN - SCOPUS:105047275037
SN - 1682-1750
VL - 49
SP - 1435
EP - 1442
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
IS - B3-2026
T2 - 25th ISPRS Congress 2026 "From Imagery to Understanding"
Y2 - 4 July 2026 through 11 July 2026
ER -