chaytonmin / DeepMVS

3D reconstruction project with MVSNets for depth inferring.
GNU General Public License v3.0
138 stars 25 forks source link

Import output from CasMVSNet to OpenMVS #2

Open jetdapr opened 2 years ago

jetdapr commented 2 years ago

Hi, thank you for contributing to this repository. It's worth using deep learning approaches to improve the quality of the sparse point cloud before densification and the rest. How did you manage the output from CasMVSNet or another depth inferring method in order to use it in the OpenMVS step? Any data modification or libraries required? Thank you.

chaytonmin commented 2 years ago

Hi, thank you for contributing to this repository. It's worth using deep learning approaches to improve the quality of the sparse point cloud before densification and the rest. How did you manage the output from CasMVSNet or another depth inferring method in order to use it in the OpenMVS step? Any data modification or libraries required? Thank you.

I export the depth-maps as DMAP files for OpenMVS

helloycr commented 2 years ago

Hello, how can I convert the depth data file obtained by the deep learning network into the dmap format file required by openmvs? Can you send me the code for this? I would be grateful if I could. My contact information is 917318329@qq.com

chaytonmin commented 2 years ago

Hello, how can I convert the depth data file obtained by the deep learning network into the dmap format file required by openmvs? Can you send me the code for this? I would be grateful if I could. My contact information is 917318329@qq.com

You can refer to this : https://github.com/cdcseacave/openMVS/blob/master/libs/MVS/Interface.h#L631