This the Pytorch implementation of our work on depth completion.
S. Zhao, M. Gong, H. Fu and D. Tao. Adaptive Context-Aware Multi-Modal Network for Depth Completion. PAPER
- Python 3.6
- PyTorch 1.2.0
- CUDA 10.0
- Ubuntu 16.04
- Opencv-python
- pip install pointlib/.
Prepare the dataset according to the datalists (*.txt in datasets)
datasets
|----kitti
|----depth_selection
|----val_selection_cropped
|----...
|----test_depth_completion_anonymous
|----...
|----rgb
|----2011_09_26
|----...
|----train
|----2011_09_26_drive_0001_sync
|----...
We will release the training code after the peer-review process.
run
bash run_eval.sh
Note that, currently we only release the pretrained model with 32 channels.
Shanshan Zhao: szha4333@uni.sydney.edu.au or sshan.zhao00@gmail.com