# Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing

arXiv: https://arxiv.org/abs/2404.18924 · HTML: https://mlsanity.com/paper/2404.18924/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Tutel: Adaptive Mixture-of-Experts at Scale](https://mlsanity.com/paper/2206.03382/) (2022)
- [EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis](https://mlsanity.com/paper/1612.07919/) (2016)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2203.14216/) (2022)
- [Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2011.09766/) (2020)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery](https://mlsanity.com/paper/2201.11192/) (2022)
- [Frequency-Adaptive Pan-Sharpening with Mixture of Experts](https://mlsanity.com/paper/2401.02151/) (2024)
- [SeasoNet: A Seasonal Scene Classification, segmentation and Retrieval dataset for satellite Imagery over Germany](https://mlsanity.com/paper/2207.09507/) (2022)
- [High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network](https://mlsanity.com/paper/2010.00472/) (2020)
- [Handheld Burst Super-Resolution Meets Multi-Exposure Satellite Imagery](https://mlsanity.com/paper/2303.05879/) (2023)

## Built on by (most cited first, 7 of 7)

- [Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation](https://mlsanity.com/paper/2604.13761/) (2026)
- [Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images](https://mlsanity.com/paper/2505.24799/) (2025)
- [Mixture-of-Experts in Remote Sensing: A Survey](https://mlsanity.com/paper/2604.03342/) (2026)
- [Spatial-Frequency Gated Swin Transformer for Cross-Sensor Remote Sensing Super-Resolution](https://mlsanity.com/paper/2605.09687/) (2026)
- [SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution](https://mlsanity.com/paper/2605.25892/) (2026)
- [NGram-MoSE: Efficient Remote Sensing Super-Resolution via N-Gram Context and Mixture-of-Experts](https://mlsanity.com/paper/2606.08535/) (2026)
- [FaceMoE: Mixture of Experts for Low-Resolution Face Recognition](https://mlsanity.com/paper/2606.32040/) (2026)

## Abstract (arXiv)

Due to the limitations of current optical and sensor technologies and the high cost of updating them, the spectral and spatial resolution of satellites may not always meet desired requirements. For these reasons, Remote-Sensing Single-Image Super-Resolution (RS-SISR) techniques have gained significant interest. In this paper, we propose Swin2-MoSE model, an enhanced version of Swin2SR. Our model introduces MoE-SM, an enhanced Mixture-of-Experts (MoE) to replace the Feed-Forward inside all Transformer block. MoE-SM is designed with Smart-Merger, and new layer for merging the output of individual experts, and with a new way to split the work between experts, defining a new per-example strategy instead of the commonly used per-token one. Furthermore, we analyze how positional encodings interact with each other, demonstrating that per-channel bias and per-head bias can positively cooperate. Finally, we propose to use a combination of Normalized-Cross-Correlation (NCC) and Structural Similarity Index Measure (SSIM) losses, to avoid typical MSE loss limitations. Experimental results demonstrate that Swin2-MoSE outperforms any Swin derived models by up to 0.377 - 0.958 dB (PSNR) on task of 2x, 3x and 4x resolution-upscaling (Sen2Venus and OLI2MSI datasets). It also outperforms SOTA models by a good margin, proving to be competitive and with excellent potential, especially for complex tasks. Additionally, an analysis of computational costs is also performed. Finally, we show the efficacy of Swin2-MoSE, applying it to a semantic segmentation task (SeasoNet dataset). Code and pretrained are available on https://github.com/IMPLabUniPr/swin2-mose/tree/official_code