Skip to content

Implement of "Cross-domain Spacecraft Component Segmentation Based on Edge Consistency Generative Neural Network"

License

Notifications You must be signed in to change notification settings

wuaodi/cross-domain_spacecraft_segmentation

 
 

Repository files navigation

Implement of "Cross-domain Spacecraft Component Segmentation Based on Edge Consistency Generative Neural Network".

Authors: Aodi Wu, Jianhong Zuo, Shengyang Zhang and Xue Wan

paper

Accepted by The 17th International Conference on Digital Image Processing (ICDIP 2025)

core code

# edge loss
models/edgeloss.py
models/cycle_gan_model.py

# yolo bbox results to SAM
SAM/bbox_to_seg.py

training and testing

refering to:

CycleGAN: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix

YOLO: https://github.com/ultralytics/yolov5

SAM: https://github.com/facebookresearch/segment-anything

About

Implement of "Cross-domain Spacecraft Component Segmentation Based on Edge Consistency Generative Neural Network"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 88.0%
  • Jupyter Notebook 7.6%
  • Shell 2.4%
  • Other 2.0%