GASDA

This is the PyTorch implementation for our CVPR'19 paper:

S. Zhao, H. Fu, M. Gong and D. Tao. Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation. PAPER POSTER

Environment

Python 3.6
PyTorch 0.4.1
CUDA 9.0
Ubuntu 16.04

Datasets

KITTI

vKITTI

Prepare the two datasets according to the datalists (*.txt in datasets)

Training (Tesla V100, 16GB)

Train CycleGAN using the official experimental settings, or download our pretrained models.
Train F_t

python train.py --model ft --gpu_ids 0 --batchSize 8 --loadSize 256 1024 --g_tgt_premodel ./cyclegan/G_Tgt.pth

Train F_s

python train.py --model fs --gpu_ids 0 --batchSize 8 --loadSize 256 1024 --g_src_premodel ./cyclegan/G_Src.pth

Train GASDA using the pretrained F_s, F_t and CycleGAN.

python train.py --freeze_bn --freeze_in --model gasda --gpu_ids 0 --batchSize 3 --loadSize 192 640 --g_src_premodel ./cyclegan/G_Src.pth --g_tgt_premodel ./cyclegan/G_Tgt.pth --d_src_premodel ./cyclegan/D_Src.pth --d_tgt_premodel ./cyclegan/D_Tgt.pth --t_depth_premodel ./checkpoints/vkitti2kitti_ft_bn/**_net_G_Depth_T.pth --s_depth_premodel ./checkpoints/vkitti2kitti_fs_bn/**_net_G_Depth_S.pth

Note: this training strategy is different from that in our paper.

Test

MODELS.

Citation

If you use this code for your research, please cite our paper.

@inproceedings{zhao2019geometry,
  title={Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation},
  author={Zhao, Shanshan and Fu, Huan and Gong, Mingming and Tao, Dacheng},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={9788--9798},
  year={2019}
}

Acknowledgments

Code is inspired by T^2Net and CycleGAN.

Contact

Shanshan Zhao: szha4333@uni.sydney.edu.au or sshan.zhao00@gmail.com

TKKim93/GASDA