Giters

loicland / superpoint_graph

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The influence of pruning

baixiao930 opened this issue · comments

commented

Thanks for your excellent work.
I am confused about the influence of the pruning operation. The evaluation of partition (BR and BP metric) is based on the pruned points, which means a direct comparison between with no pruning and pruning with some voxel width is not fair. Is that true? If yes, how much influence does `without pruning' have on the partition results?

commented

Hi!

We are releasing a new version of SuperPoint Graph called SuperPoint Transformer (SPT).
It is better in any way:

✨ SPT in numbers ✨
📊 SOTA results: 76.0 mIoU S3DIS 6-Fold, 63.5 mIoU on KITTI-360 Val, 79.6 mIoU on DALES
🦋 212k parameters only!
⚡ Trains on S3DIS in 3h on 1 GPU
⚡ Preprocessing is x7 faster than SPG!
🚀 Easy install (no more boost!)

If you are interested in lightweight, high-performance 3D deep learning, you should check it out. In the meantime, we will finally retire SPG and stop maintaining this repo.