This is a TensorFlow implementation for Global Convolutional Neural Networks With Self-Attention for Fisheye Image Rectification.
This work has been published in IEEE Access.
git clone https://github.com/byunghyun23/GSAFE
pip install -r requirements.txt
Before training a model, you need to download the dataset here or full Places2.
Then, move the downloaded images to
--data/images
Run
python data_generator.py
python data_splitter.py
to distort and split the fisheye dataset. The distorted fisheye images will be placed in
--data/distorted
and split fisheye images will be placed in
--data/train_input
--data/train_target
--data/test_input
--data/test_target
python train.py
python test.py
You can use your fisheye image. Before Start, make sure that the fisheye image have been placed in
--sample
Run
python calib.py
After rectification, the results will be placed in
--results
Additionally, you can also use the model using Gradio.
python web.py