Imagefusion Rfn Nest
| Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
|---|---|---|---|---|---|---|---|---|---|---|
| Siamrpn_plus_plus_pytorch | 390 | 4 years ago | 11 | Python | ||||||
| SiamRPN, SiamRPN++, unofficial implementation of "SiamRPN++" (CVPR2019), multi-GPUs, LMDB. | ||||||||||
| Multiview Human Pose Estimation Pytorch | 388 | 2 years ago | 6 | mit | Python | |||||
| This is an official Pytorch implementation of "Cross View Fusion for 3D Human Pose Estimation, ICCV 2019". | ||||||||||
| Ffa Net | 286 | 2 years ago | 16 | Python | ||||||
| FFA-Net: Feature Fusion Attention Network for Single Image Dehazing | ||||||||||
| Vit Explain | 260 | a year ago | 8 | mit | Python | |||||
| Explainability for Vision Transformers | ||||||||||
| Dfnet | 213 | a month ago | other | Python | ||||||
| :art: Deep Fusion Network for Image Completion - ACMMM 2019 | ||||||||||
| Dss Pytorch | 141 | 4 years ago | 25 | mit | Jupyter Notebook | |||||
| :star: PyTorch implement of Deeply Supervised Salient Object Detection with Short Connection | ||||||||||
| Rtfnet | 102 | a year ago | 2 | mit | Python | |||||
| RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes | ||||||||||
| Df Net | 85 | a year ago | Python | |||||||
| Open source code for ACL 2020 Paper "Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog" | ||||||||||
| Imagefusion Rfn Nest | 63 | 3 months ago | 8 | Python | ||||||
| RFN-Nest(Information Fusion, 2021) - PyTorch =1.5，Python=3.7 | ||||||||||
| Mvsnet_pytorch | 61 | 4 years ago | 5 | Python | ||||||
| PyTorch Implementation of MVSNet | ||||||||||
RFN-Nest: An end-to-end residual fusion network for infrared and visible images
Hui Li, Xiao-Jun Wu*, Josef Kittler
Information Fusion (IF:13.669), Volume: 73, Pages: 72-86, September 2021
paper
arXiv
Supplementary Material
Platform
Python 3.7
Pytorch 1.5
The testing datasets are included in "images".
The results iamges are included in "outputs".
Training Dataset
MS-COCO 2014 (T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick. Microsoft coco: Common objects in context. In ECCV, 2014. 3-5.) is utilized to train our auto-encoder network.
KAIST (S. Hwang, J. Park, N. Kim, Y. Choi, I. So Kweon, Multispectral pedestrian detection: Benchmark dataset and baseline, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 10371045.) is utilized to train the RFN modules.
Fusion framework
Decoder architecture
Training RFN modules
Fusion results
RFN for RGBT tracking - framework
RFN for RGBT tracking - results
If you have any question about this code, feel free to reach me([email protected])
Citation
@article{li2021rfn,
title={RFN-Nest: An end-to-end residual fusion network for infrared and visible images},
author={Li, Hui and Wu, Xiao-Jun and Kittler, Josef},
journal={Information Fusion},
volume={73},
pages={72--86},
month={March},
year={2021},
publisher={Elsevier}
}
A clerical error in our paper
I am very sorry about this clerical error. Actually, in Section 4.6, this part "With the nest connection, the decoder is able to preserve more image information conveyed by the multiscale deep features (, , ) and generate more natural and clearer fused image (, , )." should change to "With the nest connection, the decoder is able to preserve more image information conveyed by the multiscale deep features (, Nabf, MS-SSIM) and generate more natural and clearer fused image (, , SCD)."
