RayMVSNet

RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo

Junhua Xi* Yifei Shi* Yijie Wang Yulan Guo Kai Xu†

National University of Defense Technology

How to use

Environment

CUDA 11.2
Python 3.8.5
torch 1.7.1+cu110
pip install -r requirements.txt

Data

Download the preprocessed DTU data and unzip it to data/dtu.

./dtu  
      ├── Rectified                 
      │   ├── scan1_train       
      │   ├── scan2_train       
      │   └── ...                
      ├── Cameras
      │   ├── pair.txt   
      │   ├── train   
      │       ├── 00000000_cam.txt   
      │       ├── 00000001_cam.txt   
      │       └── ...  
      └── Depths         
          ├── scan1_train   
          ├── scan2_train    
          └── ...

Training

Train the network
python train.py

Testing

python test.py

You can test with the pretrained model: ./model.ckpt

Depth Fusion

Testing process generates per-view depth map. We need to apply depth fusion fusion.py to get the complete point cloud. Please refer to MVSNet for more details.

python fusion.py

Evaluation

Download the offical evaluation tool from DTU benchmark
We provide our pre-computed point clouds for your convenience

Airobin329/RayMVSNet