mvpnet
mvpnet copied to clipboard
maxjaritz
Implementation of the paper "Multi-view PointNet for 3D Scene Understanding"
Can someone give me a pretrained model? Is it impossible because of scanNet's license?
Dear Mr. Jaritz, When I was reproducing the paper, there was an overfitting phenomenon when training a 2D network. The mIOU of 2D image semantic segmentation was only about 50%,...
Hi @maxjaritz, first thanks for your wonderful work! I plan to use KPConv to replace PointNet++ to do some experiments. I want to know whether the multi-view feature augmented point...
