NODiff: Neural Operator Diffusion for Multispectral Image Fusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4753-4761
DOI: 10.1609/aaai.v40i6.42477 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Junming Hou und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Pansharpening is a powerful technique for generating high-resolution multispectral (HRMS) images by fusing currently available image pairs of low-resolution multispectral (LRMS) and texture-rich panchromatic (PAN) data, effectively addressing the physical constraints of satellite sensors. While recent generative diffusion models have demonstrated impressive performance gains in this domain, their prohibitive computational demands and training costs hinder practicality in resource-constrained remote sensing satellite systems. In this work, we propose NODiff, a novel diffusion framework that replaces the conventional attention-based denoising backbone with a neural operator, seamlessly integrating operator learning and generative modeling into an efficient yet effective solution for pansharpening. In practice, we implement our approach through a two-stage learning paradigm: First, we pretrain the proposed Neural Operator-based diffusion model to learn the high-resolution texture priors essential for pansharpening. Afterward, we freeze the pretrained parameters, and design a lightweight conditional detail guidance adapter to enable efficient fine-tuning for generating desired HRMS images. Meanwhile, a time-aware low-rank adaptation is introduced to dynamically refine high-frequency details potentially affected by spectral mode truncation. Extensive experiments on multiple benchmark datasets demonstrate that NODiff achieves competitive pansharpening performance while significantly reducing training and inference costs. Beyond pansharpening, our method provides new insights into building resource-efficient generative models.
Zitieren
APA
Hou, J., Ran, R., Chen, S., Chen, Z., Cong, X., Li, J., & Deng, L. (2026). NODiff: Neural Operator Diffusion for Multispectral Image Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4753-4761. https://doi.org/10.1609/aaai.v40i6.42477
Vancouver
Hou J, Ran R, Chen S, Chen Z, Cong X, Li J, et al. NODiff: Neural Operator Diffusion for Multispectral Image Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4753-4761. doi:10.1609/aaai.v40i6.42477
BibTeX
@article{Hou2026,
author = {Hou, Junming and Ran, Ran and Chen, Sixing and Chen, Zihao and Cong, Xiaofeng and Li, Junling and Deng, Liang-Jian},
title = {NODiff: Neural Operator Diffusion for Multispectral Image Fusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {6},
pages = {4753--4761},
doi = {10.1609/aaai.v40i6.42477}
}
EUVIMED