Abstract | ||
---|---|---|
In this paper we address the task of infrared and visible image registration in complex scenes. Due to the difference of infrared and visible images, it is neither easy to reliably find features nor suitable for directly training in deep learning architecture. Thus, we propose a two-stage adversarial network, which first conducts a multi-spectral image transfer to obtain a mapped image. And then the proposed network incorporate a transformer module into the conditional adversarial network architecture to get the refined warped image. Our method can back propagate the multi-spectral registration loss and achieve end-to-end training. Experiments on our multi-spectral dataset demonstrate that this approach is effective and robust, which outperforms other state-of-the-art methods. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Image Registration, Multi-spectrum, Generative Adversarial Networks, Infrared Image |
Field | DocType | ISSN |
Computer vision,Architecture,Pattern recognition,Task analysis,Computer science,Transformer,Network architecture,Feature extraction,Artificial intelligence,Deep learning,Infrared,Image registration | Conference | 1522-4880 |
Citations | PageRank | References |
1 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lan Wang | 1 | 9 | 2.19 |
Chenqiang Gao | 2 | 23 | 8.86 |
Yue Zhao | 3 | 58 | 28.59 |
Tiecheng Song | 4 | 217 | 29.55 |
Qi Feng | 5 | 10 | 1.91 |