TY - JOUR
T1 - ZT-D2SR
T2 - dual-domain guided adaptive super-resolution for remote sensing images
AU - Cao, Xuke
AU - Zhang, Huaping
AU - Geng, Guotong
AU - Lei, Shuai
AU - Hamdulla, Askar
AU - Cao, Yunbo
AU - Luo, Zhunchen
AU - Gao, Chunxiao
AU - Zhang, Quan
N1 - Publisher Copyright:
© 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved. This article is available under the terms of the IOP-Standard License.
PY - 2026/10
Y1 - 2026/10
N2 - Remote sensing image super-resolution aims to recover high-frequency details from low-resolution (LR) images. However, when processing complex terrains and tiny objects, existing methods often struggle with insufficient detail recovery, structural distortion, and limited generalization. Although diffusion models possess powerful generative priors, their direct application to the remote sensing domain suffers from high computational costs, false textures, and structural deformations. To address these issues, this paper proposes a dual-domain guided adaptive super-resolution method. Unlike conventional methods that mainly optimize in a single domain, our method builds an efficient adaptive generation framework that improves robustness to complex unknown degradations while reducing the number of reverse-diffusion evaluations. Specifically, we extract a spatial structural feature map from the LR image and use it as geometric guidance for the adaptive initialization. We further integrate a wavelet-domain loss with pixel, perceptual, and adversarial losses to explicitly constrain frequency-specific reconstruction errors. Experiments on multiple benchmark datasets demonstrate a favorable trade-off among structural preservation, perceptual quality, and inference efficiency. The method is competitive on distortion-oriented metrics and shows advantages on selected perception-oriented and no-reference metrics.
AB - Remote sensing image super-resolution aims to recover high-frequency details from low-resolution (LR) images. However, when processing complex terrains and tiny objects, existing methods often struggle with insufficient detail recovery, structural distortion, and limited generalization. Although diffusion models possess powerful generative priors, their direct application to the remote sensing domain suffers from high computational costs, false textures, and structural deformations. To address these issues, this paper proposes a dual-domain guided adaptive super-resolution method. Unlike conventional methods that mainly optimize in a single domain, our method builds an efficient adaptive generation framework that improves robustness to complex unknown degradations while reducing the number of reverse-diffusion evaluations. Specifically, we extract a spatial structural feature map from the LR image and use it as geometric guidance for the adaptive initialization. We further integrate a wavelet-domain loss with pixel, perceptual, and adversarial losses to explicitly constrain frequency-specific reconstruction errors. Experiments on multiple benchmark datasets demonstrate a favorable trade-off among structural preservation, perceptual quality, and inference efficiency. The method is competitive on distortion-oriented metrics and shows advantages on selected perception-oriented and no-reference metrics.
KW - adaptive reconstruction
KW - dual-domain guidance
KW - frequency-domain constraint
KW - remote sensing image super-resolution
KW - structural prior
UR - https://www.scopus.com/pages/publications/105054607707
U2 - 10.1088/1361-6501/aeb4d5
DO - 10.1088/1361-6501/aeb4d5
M3 - Article
AN - SCOPUS:105054607707
SN - 0957-0233
VL - 37
JO - Measurement Science and Technology
JF - Measurement Science and Technology
IS - 43
M1 - 435402
ER -