Fast Kernel-Space Diffusion for Remote Sensing Pansharpening

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jin, Hancong, Cao, Zihan, Deng, Liang-jian, Li, Jingjing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909053130637312
author Jin, Hancong
Cao, Zihan
Deng, Liang-jian
Li, Jingjing
author_facet Jin, Hancong
Cao, Zihan
Deng, Liang-jian
Li, Jingjing
contents Pansharpening seeks to fuse high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) images into a single image with both fine spatial and rich spectral detail. Despite progress in deep learning-based approaches, existing methods often fail to capture global priors inherent in remote sensing data distributions. Diffusion-based models have recently emerged as promising solutions due to their powerful distribution mapping capabilities, however, they suffer from heavy inference latency. We introduce KSDiff, a fast kernel-space diffusion framework that generates convolutional kernels enriched with global context to enhance pansharpening quality and accelerate inference. Specifically, KSDiff constructs these kernels through the integration of a low-rank core tensor generator and a unified factor generator, orchestrated by a structure-aware multi-head attention mechanism. We further introduce a two-stage training strategy tailored for pansharpening, facilitating integration into existing pansharpening architectures. Experiments show that KSDiff achieves superior performance compared to recent promising methods, and with over $500 \times$ faster inference than diffusion-based pansharpening baselines. Ablation studies, visualizations and further evaluations substantiate the effectiveness of our approach. Code will be released upon possible acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18991
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast Kernel-Space Diffusion for Remote Sensing Pansharpening
Jin, Hancong
Cao, Zihan
Deng, Liang-jian
Li, Jingjing
Computer Vision and Pattern Recognition
Pansharpening seeks to fuse high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) images into a single image with both fine spatial and rich spectral detail. Despite progress in deep learning-based approaches, existing methods often fail to capture global priors inherent in remote sensing data distributions. Diffusion-based models have recently emerged as promising solutions due to their powerful distribution mapping capabilities, however, they suffer from heavy inference latency. We introduce KSDiff, a fast kernel-space diffusion framework that generates convolutional kernels enriched with global context to enhance pansharpening quality and accelerate inference. Specifically, KSDiff constructs these kernels through the integration of a low-rank core tensor generator and a unified factor generator, orchestrated by a structure-aware multi-head attention mechanism. We further introduce a two-stage training strategy tailored for pansharpening, facilitating integration into existing pansharpening architectures. Experiments show that KSDiff achieves superior performance compared to recent promising methods, and with over $500 \times$ faster inference than diffusion-based pansharpening baselines. Ablation studies, visualizations and further evaluations substantiate the effectiveness of our approach. Code will be released upon possible acceptance.
title Fast Kernel-Space Diffusion for Remote Sensing Pansharpening
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.18991