How does the the T-Net achieve translation invariance?

charlesq34 / pointnet

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Other

4.64k stars 1.44k forks source link

How does the the T-Net achieve translation invariance? #314

Open ywangwxd opened 1 month ago

ywangwxd commented 1 month ago

I understand the t-net can estimate a 3x3 matrix for affine transformation, but 3x3 transformation is not translation invariant. I am wondering how t-net achieve this.