Skip to content

the tf version of D2HC-RMVSNet(ECCV2020 Spotlight). Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

License

Notifications You must be signed in to change notification settings

JiadiLee/D2HC-RMVSNet

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

how to use:

Installation

  • Check out the source code git clone https://github.com/haibao637/D2HC-RMVSNet
  • Install cuda , cudnn and python 2.7
  • Install Tensorflow and other dependencies by sudo pip install -r requirements.txt
  • Download
  • Preprocessed training/validation data: BlendedMVS, DTU and ETH3D. More training resources could be found in BlendedMVS github page
  • Preprocessed testing data: DTU testing set, Tanks and Temples testing set and training set

dataset preparation:

see https://github.com/YoYo000/MVSNet

Train the network python train.py

python train.py # make sure the dataset/log/.. path is correct

Test the network

python test.py --dense_folder = your test img directory

About

the tf version of D2HC-RMVSNet(ECCV2020 Spotlight). Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%