# Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

arXiv: https://arxiv.org/abs/2603.00543 · HTML: https://mlsanity.com/paper/2603.00543/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 28 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [FlexiViT: One Model for All Patch Sizes](https://mlsanity.com/paper/2212.08013/) (2022)
- [Pan-Mamba: Effective pan-sharpening with State Space Model](https://mlsanity.com/paper/2402.12192/) (2024)
- [Improving Image Restoration by Revisiting Global Information Aggregation](https://mlsanity.com/paper/2112.04491/) (2021)
- [A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening](https://mlsanity.com/paper/1712.09809/) (2017)
- [Deep Gradient Projection Networks for Pan-sharpening](https://mlsanity.com/paper/2103.04584/) (2021)
- [ResFormer: Scaling ViTs with Multi-Resolution Training](https://mlsanity.com/paper/2212.00776/) (2022)
- [ViTAR: Vision Transformer with Any Resolution](https://mlsanity.com/paper/2403.18361/) (2024)
- [FusionMamba: Efficient Remote Sensing Image Fusion with State Space Model](https://mlsanity.com/paper/2404.07932/) (2024)
- [PanFlowNet: A Flow-Based Deep Network for Pan-sharpening](https://mlsanity.com/paper/2305.07774/) (2023)
- [A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion](https://mlsanity.com/paper/2404.09293/) (2024)
- [Adaptive Rectangular Convolution for Remote Sensing Pansharpening](https://mlsanity.com/paper/2503.00467/) (2025)
- [Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion](https://mlsanity.com/paper/2409.01728/) (2024)
- [MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution](https://mlsanity.com/paper/2405.18240/) (2024)
- [Self-supervised Multiplex Consensus Mamba for General Image Fusion](https://mlsanity.com/paper/2512.20921/) (2025)

## Built on by (most cited first, 2 of 2)

- [Universal Pansharpening Model](https://mlsanity.com/paper/2603.03831/) (2026)
- [Dual Modality Prompted Diffusion Priors for Zero Shot Hyperspectral Pansharpening](https://mlsanity.com/paper/2608.11748/) (2026)

## Abstract (arXiv)

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.