search

XuyangBai / PointDSC

[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465
243 stars 37 forks source link

question about the number of input points #10

Closed dreamcubeblock closed 3 years ago

dreamcubeblock commented 3 years ago

the number of input points between train and test is different,and each one in the test set is different.If i scale it to 5000,will it effect the final result?

XuyangBai commented 3 years ago

Hi thanks for your interest in our work. The network is able to handle inputs of different size and we use 1000 points during training for a larger batch_size. During inference, my experience is more points you have, the better performance you will get (but with a larger memory and computation cost).

dreamcubeblock commented 3 years ago

So if we want to compair with your method on 3dmatch testset,we have to