/SegMiF

ICCV2023 | Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation

Primary LanguagePython

SegMiF

Jinyuan Liu, Zhu Liu, Guanyao Wu, Long Ma, Risheng Liu, Wei Zhong, Zhongxuan Luo, Xin Fan*,“Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation”, International Conference on Computer Vision (ICCV), 2023. (Oral)


FMB Dataset

Preview

The preview of our FMB dataset is as follows.


preview


Download

SegMiF Fusion

Set Up on Your Own Machine

When you want to dive deeper or apply it on a larger scale, you can configure our SegMiF on your computer by following the steps below.

Virtual Environment

We strongly recommend that you use Conda as a package manager.

# create virtual environment
conda create -n SegMiF python=3.10
conda activate SegMiF
# select pytorch version yourself
# install SegMiF requirements
pip install -r requirements.txt

Data Preparation

Related data, checkpoint, and our results on MFNet Dataset can be downloaded in

Citation

If this work has been helpful to you, please feel free to cite our paper!

@inproceedings{liu2023segmif,
  title={Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation},
  author={Liu, Jinyuan and Liu, Zhu and Wu, Guanyao and Ma, Long and Liu, Risheng and Zhong, Wei and Luo, Zhongxuan and Fan, Xin},
  booktitle={International Conference on Computer Vision},
  year={2023}
}