The datasets used to train and evaluate our GMFlow model are as follows:
By default the dataloader dataloader/flow/datasets.py assumes the datasets are located in the datasets directory.
It is recommended to symlink your dataset root to datasets:
ln -s $YOUR_DATASET_ROOT datasets
Otherwise, you may need to change the corresponding paths in dataloader/flow/datasets.py.
The datasets used to train and evaluate our GMStereo model are as follows:
- Scene Flow
- Virtual KITTI 2
- KITTI
- TartanAir
- Falling Things
- HR-VS
- CREStereo Dataset
- InStereo2K
- Middlebury
- Sintel Stereo
- ETH3D
By default the dataloader dataloader/stereo/datasets.py assumes the datasets are located in the datasets directory.
It is recommended to symlink your dataset root to datasets:
ln -s $YOUR_DATASET_ROOT datasets
Otherwise, you may need to change the corresponding paths in dataloader/stereo/datasets.py.
The datasets used to train and evaluate our GMDepth model are as follows:
We support downloading and extracting the DeMoN dataset in our code: dataloader/depth/download_demon_train.sh, dataloader/depth/download_demon_test.sh, dataloader/depth/prepare_demon_train.sh and dataloader/depth/prepare_demon_test.sh.
By default the dataloader dataloader/depth/datasets.py assumes the datasets are located in the datasets directory.
It is recommended to symlink your dataset root to datasets:
ln -s $YOUR_DATASET_ROOT datasets
Otherwise, you may need to change the corresponding paths in dataloader/depth/datasets.py.