Official codes of CVPR 2023 Paper | Fully Self-Supervised Depth Estimation from Defocus Clue
Create a new environment and install dependencies with requirement.txt:
conda create -n dered
conda activate dered
conda install --file requirements.txt
python gauss_psf/setup.py installThe generation code for NYUv2 Focal Stack dataset is provided.
The generation code for DefocusNet can be found here.
You can download the model weights trained on NYUv2 Focal Stack from here.
python scripts/train.py --data_path [path/to/dataset] --dataset [Dataset] --recon_all \
-N [experiment_name] --use_cuda -E 1000 --BS 32 --save_checkpoint --save_best --save_last \
--sm_loss_beta 2.5 --verbose --recon_loss_lambda 1e3 --aif_blur_loss_lambda 10 \
--blur_loss_lambda 1e1 --sm_loss_lambda 1e1 --log --vispython scripts/train.py --data_path [path/to/dataset] --dataset [Dataset] --recon_all \
-N [experiment_name] --use_cuda --BS 32 --save_best --verbose --evalParts of the code are developed from DefocusNet and UnsupervisedDepthFromFocus.
@article{si2023fully,
title={Fully Self-Supervised Depth Estimation from Defocus Clue},
author={Si, Haozhe and Zhao, Bin and Wang, Dong and Gao, Yupeng and Chen, Mulin and Wang, Zhigang and Li, Xuelong},
journal={arXiv preprint arXiv:2303.10752},
year={2023}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent