# Guided Deep Decoder: Unsupervised Image Pair Fusion

arXiv: https://arxiv.org/abs/2007.11766 · HTML: https://mlsanity.com/paper/2007.11766/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 20 of 20)

- [Multimodal Alignment and Fusion: A Survey](https://mlsanity.com/paper/2411.17040/) (2024)
- [Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review](https://mlsanity.com/paper/2205.01380/) (2022)
- [Guided Depth Super-Resolution by Deep Anisotropic Diffusion](https://mlsanity.com/paper/2211.11592/) (2022)
- [Learning Graph Regularisation for Guided Super-Resolution](https://mlsanity.com/paper/2203.14297/) (2022)
- [Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion](https://mlsanity.com/paper/2205.03742/) (2022)
- [Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution](https://mlsanity.com/paper/2207.09156/) (2022)
- [Anatomical-Guided Attention Enhances Unsupervised PET Image Denoising Performance](https://mlsanity.com/paper/2109.00802/) (2021)
- [Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2110.11591/) (2021)
- [Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity](https://mlsanity.com/paper/2307.14403/) (2023)
- [Hyperspectral Pansharpening: Critical Review, Tools and Future Perspectives](https://mlsanity.com/paper/2407.01355/) (2024)
- [Perspective-Equivariance for Unsupervised Imaging with Camera Geometry](https://mlsanity.com/paper/2403.09327/) (2024)
- [Hyperspectral and Multispectral Image Fusion Using the Conditional Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2307.03423/) (2023)
- [LDP-Net: An Unsupervised Pansharpening Network Based on Learnable Degradation Processes](https://mlsanity.com/paper/2111.12483/) (2021)
- [Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing](https://mlsanity.com/paper/2103.01449/) (2021)
- [Guided Deep Generative Model-based Spatial Regularization for Multiband Imaging Inverse Problems](https://mlsanity.com/paper/2306.17197/) (2023)
- [Unsupervised Hyperspectral and Multispectral Images Fusion Based on the Cycle Consistency](https://mlsanity.com/paper/2307.03413/) (2023)
- [Degradation Alchemy: Self-Supervised Unknown-to-Known Transformation for Blind Hyperspectral Image Fusion](https://mlsanity.com/paper/2503.14892/) (2025)
- [DIPLI: Deep Image Prior Lucky Imaging for Blind Astronomical Image Restoration](https://mlsanity.com/paper/2503.15984/) (2025)
- [Capturing Fine-Grained Alignments Improves 3D Affordance Detection](https://mlsanity.com/paper/2506.19312/) (2025)
- [Learning Spatial-Spectral Refinement and Calibrating Complementary Observations for Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/2609.05303/) (2026)

## Abstract (arXiv)

The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific handcrafted prior and did not address the problems with a unified approach. To address this limitation, in this study, we propose a guided deep decoder network as a general prior. The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image. The two networks are connected by feature refinement units to embed the multi-scale features of the guidance image into the deep decoder network. The proposed network allows the network parameters to be optimized in an unsupervised way without training data. Our results show that the proposed network can achieve state-of-the-art performance in various image fusion problems.