# A Matching Algorithm based on Image Attribute Transfer and Local Features for Underwater Acoustic and Optical Images

arXiv: https://arxiv.org/abs/2108.12151 · HTML: https://mlsanity.com/paper/2108.12151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 49 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [A Closed-form Solution to Photorealistic Image Stylization](https://mlsanity.com/paper/1802.06474/) (2018)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [Visual Attribute Transfer through Deep Image Analogy](https://mlsanity.com/paper/1705.01088/) (2017)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Diversified Texture Synthesis with Feed-forward Networks](https://mlsanity.com/paper/1703.01664/) (2017)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [Improving Sonar Image Patch Matching via Deep Learning](https://mlsanity.com/paper/1709.02150/) (2017)

## Abstract (arXiv)

In the field of underwater vision research, image matching between the sonar sensors and optical cameras has always been a challenging problem. Due to the difference in the imaging mechanism between them, which are the gray value, texture, contrast, etc. of the acoustic images and the optical images are also variant in local locations, which makes the traditional matching method based on the optical image invalid. Coupled with the difficulties and high costs of underwater data acquisition, it further affects the research process of acousto-optic data fusion technology. In order to maximize the use of underwater sensor data and promote the development of multi-sensor information fusion (MSIF), this study applies the image attribute transfer method based on deep learning approach to solve the problem of acousto-optic image matching, the core of which is to eliminate the imaging differences between them as much as possible. At the same time, the advanced local feature descriptor is introduced to solve the challenging acousto-optic matching problem. Experimental results show that our proposed method could preprocess acousto-optic images effectively and obtain accurate matching results. Additionally, the method is based on the combination of image depth semantic layer, and it could indirectly display the local feature matching relationship between original image pair, which provides a new solution to the underwater multi-sensor image matching problem.