arXiv 2603.005432026-03-06cs.CV

跨尺度 pansharpening 通过 ScaleFormer 和 PanScale 数据集

Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

HFIPS, Chinese Academy of Sciences（中国科学院HFIPS）；University of Science and Technology of China（中国科学技术大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）；The University of Hong Kong（香港大学）；Xiamen University（厦门大学）；Zhejiang University（浙江大学）

Ke Cao, Xuanhua He, Xueheng Li, Lingting Zhu, Yingying Wang, Ao Ma, Zhanjie Zhang, Man Zhou, Chengjun Xie, Jie Zhang

备注：: Accepted by CVPR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 ScaleFormer 架构和 PanScale 数据集，通过跨尺度 pansharpening 方法提升多尺度场景下的图像融合质量与泛化能力。

摘要：

pansharpening 的目标是通过融合全色图像的空间细节和低分辨率多谱段数据的光谱丰富性来生成高分辨率多谱段图像。然而，大多数现有方法是在有限的低分辨率设置下评估的，限制了它们在现实世界高分辨率场景中的泛化能力。为了弥合这一差距，我们系统地研究了跨尺度 pansharpening 的数据、算法和计算挑战。我们首先介绍了 PanScale，首个大规模、跨尺度 pansharpening 数据集，同时配套 PanScale-Bench，一个用于评估在不同分辨率和尺度下泛化能力的综合基准。为了实现尺度泛化，我们提出 ScaleFormer，一种新的架构，用于多尺度 pansharpening。 ScaleFormer 将图像分辨率的泛化重新表述为序列长度的泛化：它将图像分块为相同分辨率但长度随图像尺度变化的片段序列。一个 Scale-Aware Patchify 模块使从固定大小裁剪中训练此类变化成为可能。 ScaleFormer 然后将片段内的空间特征学习与片段间的序列依赖性建模解耦，结合 Rotary Positional Encoding 来增强对未见过的尺度的外推能力。大量实验表明，我们的方法在融合质量和跨尺度泛化方面均优于现有最佳方法。数据集和源代码可在 https://github.com/caoke-963/ScaleFormer 上获得。

英文摘要：

Pansharpening aims to generate high-resolution multi-spectral images by fusing the spatial detail of panchromatic images with the spectral richness of low-resolution MS data. However, most existing methods are evaluated under limited, low-resolution settings, limiting their generalization to real-world, high-resolution scenarios. To bridge this gap, we systematically investigate the data, algorithmic, and computational challenges of cross-scale pansharpening. We first introduce PanScale, the first large-scale, cross-scale pansharpening dataset, accompanied by PanScale-Bench, a comprehensive benchmark for evaluating generalization across varying resolutions and scales. To realize scale generalization, we propose ScaleFormer, a novel architecture designed for multi-scale pansharpening. ScaleFormer reframes generalization across image resolutions as generalization across sequence lengths: it tokenizes images into patch sequences of the same resolution but variable length proportional to image scale. A Scale-Aware Patchify module enables training for such variations from fixed-size crops. ScaleFormer then decouples intra-patch spatial feature learning from inter-patch sequential dependency modeling, incorporating Rotary Positional Encoding to enhance extrapolation to unseen scales. Extensive experiments show that our approach outperforms SOTA methods in fusion quality and cross-scale generalization. The datasets and source code are available at https://github.com/caoke-963/ScaleFormer.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。