# PanFlowNet: A Flow-Based Deep Network for Pan-sharpening

arXiv: https://arxiv.org/abs/2305.07774 · HTML: https://mlsanity.com/paper/2305.07774/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 61 references that are in the map.
- First posted on arXiv 12 May 2023.

## Builds on (most cited first, 21 of 21)

- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019)
- [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)
- [Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net](https://mlsanity.com/paper/1901.03281/) (2019)
- [Memory-augmented Deep Unfolding Network for Guided Image Super-resolution](https://mlsanity.com/paper/2203.04960/) (2022)
- [Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network](https://mlsanity.com/paper/1705.07556/) (2017)
- [DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer](https://mlsanity.com/paper/1908.08074/) (2019)
- [Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network](https://mlsanity.com/paper/1705.00727/) (2017)
- [A Triple-Double Convolutional Neural Network for Panchromatic Sharpening](https://mlsanity.com/paper/2112.02237/) (2021)
- [Proximal PanNet: A Model-Based Deep Network for Pansharpening](https://mlsanity.com/paper/2203.04286/) (2022)
- [Robust Fusion of Multi-Band Images with Different Spatial and Spectral Resolutions for Change Detection](https://mlsanity.com/paper/1609.06076/) (2016)

## Built on by (most cited first, 16 of 16)

- [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)
- [Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion](https://mlsanity.com/paper/2409.01728/) (2024)
- [Scene Prior Filtering for Depth Super-Resolution](https://mlsanity.com/paper/2402.13876/) (2024)
- [Perspective-Equivariance for Unsupervised Imaging with Camera Geometry](https://mlsanity.com/paper/2403.09327/) (2024)
- [Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables](https://mlsanity.com/paper/2503.23793/) (2025)
- [SWIFT: A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening](https://mlsanity.com/paper/2507.20311/) (2025)
- [Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark](https://mlsanity.com/paper/2603.00543/) (2026)
- [Understanding Pan-Sharpening via Generalized Inverse](https://mlsanity.com/paper/2310.02718/) (2023)
- [CAT: A Conditional Adaptation Tailor for Efficient and Effective Instance-Specific Pansharpening on Real-World Data](https://mlsanity.com/paper/2504.10242/) (2025)
- [Two-Stage Random Alternation Framework for One-Shot Pansharpening](https://mlsanity.com/paper/2505.06576/) (2025)
- [Towards High-Resolution Alignment and Super-Resolution of Multi-Sensor Satellite Imagery](https://mlsanity.com/paper/2507.23150/) (2025)
- [Spatial-Spectral Binarized Neural Network for Panchromatic and Multi-spectral Images Fusion](https://mlsanity.com/paper/2509.23321/) (2025)
- [MambaX: Image Super-Resolution with State Predictive Control](https://mlsanity.com/paper/2511.18028/) (2025)
- [Universal Pansharpening Model](https://mlsanity.com/paper/2603.03831/) (2026)
- [Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening](https://mlsanity.com/paper/2604.14622/) (2026)

## Abstract (arXiv)

Pan-sharpening aims to generate a high-resolution multispectral (HRMS) image by integrating the spectral information of a low-resolution multispectral (LRMS) image with the texture details of a high-resolution panchromatic (PAN) image. It essentially inherits the ill-posed nature of the super-resolution (SR) task that diverse HRMS images can degrade into an LRMS image. However, existing deep learning-based methods recover only one HRMS image from the LRMS image and PAN image using a deterministic mapping, thus ignoring the diversity of the HRMS image. In this paper, to alleviate this ill-posed issue, we propose a flow-based pan-sharpening network (PanFlowNet) to directly learn the conditional distribution of HRMS image given LRMS image and PAN image instead of learning a deterministic mapping. Specifically, we first transform this unknown conditional distribution into a given Gaussian distribution by an invertible network, and the conditional distribution can thus be explicitly defined. Then, we design an invertible Conditional Affine Coupling Block (CACB) and further build the architecture of PanFlowNet by stacking a series of CACBs. Finally, the PanFlowNet is trained by maximizing the log-likelihood of the conditional distribution given a training set and can then be used to predict diverse HRMS images. The experimental results verify that the proposed PanFlowNet can generate various HRMS images given an LRMS image and a PAN image. Additionally, the experimental results on different kinds of satellite datasets also demonstrate the superiority of our PanFlowNet compared with other state-of-the-art methods both visually and quantitatively.