Refining Monocular Depth Estimation using PatchGAN Priors

Learning Depth for Autonomous driving from Monocular Images

Network

The repo presents an approach to refine monocular depth estimates by incorporating a patch discriminator.

To train, please run

python train.py [args]

The final results for KITTI are still pending. For the NYU dataset, it achieves a MSE of 0.03 and L1 Loss of 0.08.

Here are a few snapshots

Name		Name	Last commit message	Last commit date
Latest commit History 30 Commits
imgs		imgs
README.md		README.md
data_loader.py		data_loader.py
eigen_test_files.txt		eigen_test_files.txt
eigen_train_files.txt		eigen_train_files.txt
eigen_val_files.txt		eigen_val_files.txt
get_dataset.sh		get_dataset.sh
get_depth_maps.sh		get_depth_maps.sh
model.py		model.py
nyu_dataloader.py		nyu_dataloader.py
nyu_loader.py		nyu_loader.py
nyu_train.py		nyu_train.py
prepare_data.py		prepare_data.py
train.py		train.py
train_dorn.py		train_dorn.py
train_patchgan.py		train_patchgan.py
train_unet.py		train_unet.py
unet.py		unet.py