3 Methods Used by PointNeXt to Achieve state-of-the-art on S3DIS

Simon Buus Jensen, 2022-10-03

The last couple of months, I have been looking into the newest extension of the popular PointNet and PointNet++ architectures called PointNeXt - a deep learning architecture for solving 3D point clouds tasks e.g. classification and semantic segmentation.

PointNeXt got released back in the beginning of June this year (2022) and the PointNeXt paper very recently got accepted...

#deep learning #s3dis #3d point clouds #semantic segmentation

Mean Intersection over Union (mIoU) for 3D Semantic Segmentation

Simon Buus Jensen, 2022-07-04

The mean Intersection over Union (mIoU) is a metric which is often used for measuring the goodness of e.g. 2D- and 3D semantic segmentation and object detection systems, by comparing the predictions made by a system to the ground truth labels. In this post, we will show how the mIoU is calculated for a very simple 3D point cloud toy example...

#semantic segmentation #deep learning #metrics #miou #3d point clouds