# Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity

arXiv: https://arxiv.org/abs/2307.14403 · HTML: https://mlsanity.com/paper/2307.14403/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 74 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening](https://mlsanity.com/paper/1712.09809/) (2017)
- [Pansharpening via Detail Injection Based Convolutional Neural Networks](https://mlsanity.com/paper/1806.08898/) (2018)
- [PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening](https://mlsanity.com/paper/1805.03371/) (2018)
- [Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network](https://mlsanity.com/paper/1705.07556/) (2017)
- [Target-adaptive CNN-based pansharpening](https://mlsanity.com/paper/1709.06054/) (2017)
- [Guided Deep Decoder: Unsupervised Image Pair Fusion](https://mlsanity.com/paper/2007.11766/) (2020)
- [Pansharpening by convolutional neural networks in the full resolution framework](https://mlsanity.com/paper/2111.08334/) (2021)
- [Full-resolution quality assessment for pansharpening](https://mlsanity.com/paper/2108.06144/) (2021)
- [SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery](https://mlsanity.com/paper/2105.02400/) (2021)

## Built on by (most cited first, 8 of 8)

- [Hyperspectral Pansharpening: Critical Review, Tools and Future Perspectives](https://mlsanity.com/paper/2407.01355/) (2024)
- [Band-wise Hyperspectral Image Pansharpening using CNN Model Propagation](https://mlsanity.com/paper/2311.06510/) (2023)
- [Perspective-Equivariance for Unsupervised Imaging with Camera Geometry](https://mlsanity.com/paper/2403.09327/) (2024)
- [Enpowering Your Pansharpening Models with Generalizability: Unified Distribution is All You Need](https://mlsanity.com/paper/2510.22217/) (2025)
- [Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control](https://mlsanity.com/paper/2505.16658/) (2025)
- [Leveraging Large-Scale Pretrained Spatial-Spectral Priors for General Zero-Shot Pansharpening](https://mlsanity.com/paper/2512.02643/) (2025)
- [RAPNet: A Receptive-Field Adaptive Convolutional Neural Network for Pansharpening](https://mlsanity.com/paper/2507.10461/) (2025)
- [Perspective-Equivariant Fine-tuning for Multispectral Demosaicing without Ground Truth](https://mlsanity.com/paper/2603.01332/) (2026)

## Abstract (arXiv)

In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain. However, models trained on downsized images tend to perform poorly on high-resolution target images. For this reason, several research groups are now turning to unsupervised training in the full-resolution domain, through the definition of appropriate loss functions and training paradigms. In this context, we have recently proposed a full-resolution training framework which can be applied to many existing architectures. Here, we propose a new deep learning-based pansharpening model that fully exploits the potential of this approach and provides cutting-edge performance. Besides architectural improvements with respect to previous work, such as the use of residual attention modules, the proposed model features a novel loss function that jointly promotes the spectral and spatial quality of the pansharpened data. In addition, thanks to a new fine-tuning strategy, it improves inference-time adaptation to target images. Experiments on a large variety of test images, performed in challenging scenarios, demonstrate that the proposed method compares favorably with the state of the art both in terms of numerical results and visual output. Code is available online at https://github.com/matciotola/Lambda-PNN.