Pytorch implementation of FSLNet proposed in paper "Joint Learning of Frequency and Spatial Domains for Dense Image Prediction" by Shaocheng JIA and Wei YAO Article.
imageio 2.9.0
importlib-metadata 4.8.1
jupyter 1.0.0
matplotlib 3.4.3
notebook 6.4.3
numpy 1.20.2
opencv-python 4.5.3.56
pandas 1.3.4
Pillow 8.3.1
scikit-image 0.18.3
scikit-learn 1.0.2
scipy 1.7.1
tensorboardX 2.4
torch 1.9.1
Please refer to test.ipynb to quickly test the models.
Please refer to Monodepth2 for detailed evaluation and training.
Please find the weights trained on the KITTI dataset in weights folder.
@article{JIA202314,
title={Joint learning of frequency and spatial domains for dense image prediction},
author={Jia, Shaocheng and Yao, Wei},
journal={ISPRS Journal of Photogrammetry and Remote Sensing},
volume={195},
pages={14-28},
year={2023},
issn = {0924-2716},
publisher={Elsevier}
}