# Universal Pansharpening Model

arXiv: https://arxiv.org/abs/2603.03831 · HTML: https://mlsanity.com/paper/2603.03831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 34 of its 103 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 34)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts](https://mlsanity.com/paper/2405.11273/) (2024)
- [Pan-Mamba: Effective pan-sharpening with State Space Model](https://mlsanity.com/paper/2402.12192/) (2024)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models](https://mlsanity.com/paper/2406.06563/) (2024)
- [PanGu-Sigma: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing](https://mlsanity.com/paper/2303.10845/) (2023)
- [Rewrite the Stars](https://mlsanity.com/paper/2403.19967/) (2024)
- [Deep Gradient Projection Networks for Pan-sharpening](https://mlsanity.com/paper/2103.04584/) (2021)
- [Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models](https://mlsanity.com/paper/2404.05567/) (2024)
- [EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate](https://mlsanity.com/paper/2112.14397/) (2021)
- [HMoE: Heterogeneous Mixture of Experts for Language Modeling](https://mlsanity.com/paper/2408.10681/) (2024)
- [Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening](https://mlsanity.com/paper/2404.07543/) (2024)
- [U2Net: A General Framework with Spatial-Spectral-Integrated Double U-Net for Image Fusion](https://mlsanity.com/paper/2212.06466/) (2022)
- [PanFormer: a Transformer Based Model for Pan-sharpening](https://mlsanity.com/paper/2203.02916/) (2022)
- [PanFlowNet: A Flow-Based Deep Network for Pan-sharpening](https://mlsanity.com/paper/2305.07774/) (2023)
- [SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening](https://mlsanity.com/paper/2404.11537/) (2024)
- [Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening](https://mlsanity.com/paper/2502.04903/) (2025)
- [Hyperspectral Pansharpening: Critical Review, Tools and Future Perspectives](https://mlsanity.com/paper/2407.01355/) (2024)
- [Bidirectional Diffusion Bridge Models](https://mlsanity.com/paper/2502.09655/) (2025)
- [Linearly-evolved Transformer for Pan-sharpening](https://mlsanity.com/paper/2404.12804/) (2024)
- [Hipandas: Hyperspectral Image Joint Denoising and Super-Resolution by Image Fusion with the Panchromatic Image](https://mlsanity.com/paper/2412.04201/) (2024)
- [Infinite-Dimensional Feature Interaction](https://mlsanity.com/paper/2405.13972/) (2024)
- [Enpowering Your Pansharpening Models with Generalizability: Unified Distribution is All You Need](https://mlsanity.com/paper/2510.22217/) (2025)

## Abstract (arXiv)

Pansharpening generates the high-resolution multi-spectral (MS) image by integrating spatial details from a texture-rich panchromatic (PAN) image and spectral attributes from a low-resolution MS image. Existing methods are predominantly satellite-specific and scene-dependent, which severely limits their generalization across heterogeneous sensors and varied scenes, thereby reducing their real-world practicality. To address these challenges, we present UniPS, a universal pansharpening model for satellite-agnostic and scene-robust fusion. Specifically, we introduce a modality-interleaved transformer that learns band-wise modal specializations to form reversible spectral affine bases, mapping arbitrary-band MS into a unified latent space via tensor multiplication. Building upon this, we construct a latent diffusion bridge model to progressively evolve latent representations, and incorporate bridge posterior sampling to couple latent diffusion with pixel-space observations, enabling stable and controllable fusion. Furthermore, we devise infinite-dimensional pixel-to-latent interaction mechanisms to comprehensively capture the cross-domain dependencies between PAN observations and MS representations, thereby facilitating complementary information fusion. In addition, to support large-scale training and evaluation, we construct a comprehensive pansharpening benchmark, termed PSBench, consisting of worldwide MS and PAN image pairs from multiple satellites across diverse scenes. Extensive experiments verify that UniPS consistently outperforms state-of-the-art methods, exhibiting superior generalization and robustness across a wide range of tasks.