Code for "A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation"
- Ubuntu 16.04
- Python 2.7
- Cuda 9.0 and cudnn 7.0
- Tensorflow 1.5
- other dependencies in
requirements.txt
- Extract
model.zip
tomodel
folder - Run example
cd atvsnet python example.py
- Download preprocess ETH3D dataset from MVSNet and extract to
data
folder - Build fusible
cd fusible mkdir build cd build cmake .. make
- Produce point cloud
cd atvsnet ./reproduce_pc.sh