tp030ny/AA-RMVSNet

Code for AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network (ICCV2021).

PythonMIT

AA-RMVSNet

Code for AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network (ICCV2021) in PyTorch.

Data Preparation

Download the preprocessed DTU training data (also available at BaiduYun, PW: s2v2).
For other datasets, please follow the practice in Yao Yao's MVSNet repo.
The pretrained model is provided. Place it under ./checkpoints/.

How to run

Install required dependencies:

conda create -n drmvsnet python=3.6
conda activate drmvsnet
conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=10.0 -c pytorch
conda install -c conda-forge py-opencv plyfile tensorboardx

Set root of datasets as env variables in env.sh.
Train AA-RMVSNet on DTU dataset (note that training requires a large amount of GPU memory):
```
./scripts/train_dtu.sh
```
Predict depth maps and fuse them to get point clouds of DTU:
```
./scripts/eval_dtu.sh
./scripts/fusion_dtu.sh
```
Predict depth maps and fuse them to get point clouds of Tanks and Temples:
```
./scripts/eval_tnt.sh
./scripts/fusion_tnt.sh
```

Note: if permission issues are encountered, try chmod +x <script_filename> to allow execution.

Citation

@article{wei2021aarmvsnet,
  title={AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network},
  author={Wei, Zizhuang and Zhu, Qingtian and Min, Chen and Chen, Yisong and Wang, Guoping},
  journal={International Conference on Computer Vision (ICCV)},
  year={2021}
}

Acknowledgements

This repository is heavily based on Xiaoyang Guo's PyTorch implementation.