why nscale is different for training and testing?

ToughStoneX / Self-Supervised-MVS

Pytorch codes for "Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation"

152 stars 15 forks source link

Open ewrfcas opened 2 years ago

ewrfcas commented 2 years ago

Hi, nscale is set to 2 for the training of cvp-mvsnet, while it is 5 for the testing. Are there any reasons?