# Frequency-Adaptive Pan-Sharpening with Mixture of Experts

arXiv: https://arxiv.org/abs/2401.02151 · HTML: https://mlsanity.com/paper/2401.02151/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Builds on (most cited first, 11 of 11)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Fourier Space Losses for Efficient Perceptual Image Super-Resolution](https://mlsanity.com/paper/2106.00783/) (2021)
- [Hard Mixtures of Experts for Large Scale Weakly Supervised Vision](https://mlsanity.com/paper/1704.06363/) (2017)
- [A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening](https://mlsanity.com/paper/1712.09809/) (2017)
- [Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion](https://mlsanity.com/paper/2302.01392/) (2023)
- [Deep Gradient Projection Networks for Pan-sharpening](https://mlsanity.com/paper/2103.04584/) (2021)
- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network](https://mlsanity.com/paper/2210.08181/) (2022)

## Built on by (most cited first, 13 of 13)

- [Pan-Mamba: Effective pan-sharpening with State Space Model](https://mlsanity.com/paper/2402.12192/) (2024)
- [DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution](https://mlsanity.com/paper/2410.11666/) (2024)
- [O-Mamba: O-shape State-Space Model for Underwater Image Enhancement](https://mlsanity.com/paper/2408.12816/) (2024)
- [Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing](https://mlsanity.com/paper/2404.18924/) (2024)
- [Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion](https://mlsanity.com/paper/2409.01728/) (2024)
- [Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation](https://mlsanity.com/paper/2601.00322/) (2026)
- [Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables](https://mlsanity.com/paper/2503.23793/) (2025)
- [Enpowering Your Pansharpening Models with Generalizability: Unified Distribution is All You Need](https://mlsanity.com/paper/2510.22217/) (2025)
- [MMMamba: A Versatile Cross-Modal In Context Fusion Framework for Pan-Sharpening and Zero-Shot Image Enhancement](https://mlsanity.com/paper/2512.15261/) (2025)
- [Spatial-Spectral Binarized Neural Network for Panchromatic and Multi-spectral Images Fusion](https://mlsanity.com/paper/2509.23321/) (2025)
- [Mixture-of-Experts in Remote Sensing: A Survey](https://mlsanity.com/paper/2604.03342/) (2026)
- [CGFformer: Cluster-Guidance Frequency Transformer for Pansharpening](https://mlsanity.com/paper/2605.01490/) (2026)
- [RAFNet: Region-Aware Fusion Network for Pansharpening](https://mlsanity.com/paper/2605.02184/) (2026)

## Abstract (arXiv)

Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection with frequency domain, existing pan-sharpening research has not almost investigated the potential solution upon frequency domain. To this end, we propose a novel Frequency Adaptive Mixture of Experts (FAME) learning framework for pan-sharpening, which consists of three key components: the Adaptive Frequency Separation Prediction Module, the Sub-Frequency Learning Expert Module, and the Expert Mixture Module. In detail, the first leverages the discrete cosine transform to perform frequency separation by predicting the frequency mask. On the basis of generated mask, the second with low-frequency MOE and high-frequency MOE takes account for enabling the effective low-frequency and high-frequency information reconstruction. Followed by, the final fusion module dynamically weights high-frequency and low-frequency MOE knowledge to adapt to remote sensing images with significant content variations. Quantitative and qualitative experiments over multiple datasets demonstrate that our method performs the best against other state-of-the-art ones and comprises a strong generalization ability for real-world scenes. Code will be made publicly at urlhttps://github.com/alexhe101/FAME-Net.