Segmentation to 3D postion

[IEEE Access 2023] Official Implementation of the paper MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View

Scripts for training:

For big dataset:

python3 ./train.py -d 'big' -b 64 -j8

For small dataset:

python3 ./train.py -d 'small' -b 64 -j8

Cite this work:

@ARTICLE{10156844,
  author={Tran, Dinh Tuan and Tran, Dung Duc and Nguyen, Minh Anh and Van Pham, Quyen and Shimada, Nobutaka and Lee, Joo-Ho and Nguyen, Anh Quang},
  journal={IEEE Access}, 
  title={MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View}, 
  year={2023},
  volume={11},
  number={},
  pages={64170-64184},
  doi={10.1109/ACCESS.2023.3288027}}

minhna1112/MonoIS3Dloc

Segmentation to 3D postion

Scripts for training:

For big dataset:

For small dataset: