# Semantic Image Fusion

arXiv: https://arxiv.org/abs/2110.06697 · HTML: https://mlsanity.com/paper/2110.06697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](https://mlsanity.com/paper/1601.04589/) (2016)
- [NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models](https://mlsanity.com/paper/2007.00328/) (2020)
- [Multi-style Generative Network for Real-time Transfer](https://mlsanity.com/paper/1703.06953/) (2017)
- [Diversified Texture Synthesis with Feed-forward Networks](https://mlsanity.com/paper/1703.01664/) (2017)
- [Reveal of Vision Transformers Robustness against Adversarial Attacks](https://mlsanity.com/paper/2106.03734/) (2021)
- [Medical Image Fusion: A survey of the state of the art](https://mlsanity.com/paper/1401.0166/) (2013)
- [Infrared and Visible Image Fusion using a Deep Learning Framework](https://mlsanity.com/paper/1804.06992/) (2018)
- [Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN](https://mlsanity.com/paper/1706.03319/) (2017)
- [Texture Synthesis Using Convolutional Neural Networks](https://mlsanity.com/paper/1505.07376/) (2015)
- [A Semantic-based Medical Image Fusion Approach](https://mlsanity.com/paper/1906.00225/) (2019)
- [Image Fusion via Sparse Regularization with Non-Convex Penalties](https://mlsanity.com/paper/1905.09645/) (2019)

## Abstract (arXiv)

Image fusion methods and metrics for their evaluation have conventionally used pixel-based or low-level features. However, for many applications, the aim of image fusion is to effectively combine the semantic content of the input images. This paper proposes a novel system for the semantic combination of visual content using pre-trained CNN network architectures. Our proposed semantic fusion is initiated through the fusion of the top layer feature map outputs (for each input image)through gradient updating of the fused image input (so-called image optimisation). Simple "choose maximum" and "local majority" filter based fusion rules are utilised for feature map fusion. This provides a simple method to combine layer outputs and thus a unique framework to fuse single-channel and colour images within a decomposition pre-trained for classification and therefore aligned with semantic fusion. Furthermore, class activation mappings of each input image are used to combine semantic information at a higher level. The developed methods are able to give equivalent low-level fusion performance to state of the art methods while providing a unique architecture to combine semantic information from multiple images.