NeurOp-Diff: Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion
Zihao Xu, Yuzhi Tang, Bowen Xu, Qingquan Li
Abstract
Most publicly accessible remote sensing data suffer from low resolution, limiting their practical applications. To address this, we propose a diffusion model guided by neural operators (NO) for continuous remote sensing image super-resolution (NeurOp-Diff). Neural operators are used to learn resolution representations at arbitrary scales, encoding low-resolution (LR) images into high-dimensional features, which are then used as prior conditions to guide the diffusion model for denoising. This effectively addresses the artifacts and excessive smoothing issues present in existing super-resolution (SR) methods, enabling the generation of high-quality, continuous super-resolution images. Specifically, we adjust the super-resolution scale by a scaling factor (s), allowing the model to adapt to different super-resolution magnifications. Furthermore, experiments on multiple datasets demonstrate the effectiveness of NeurOp-Diff. Our code is available at https://github.com/zerono000/NeurOp-Diff.
BibTeX
@InProceedings{Xu_2025_ICCV,
author = {Xu, Zihao and Tang, Yuzhi and Xu, Bowen and Li, Qingquan},
title = {NeurOp-Diff: Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2025},
pages = {12491-12501}
}