how to generate the trainset'superpoint-graph after oversegment?
azsxdcfvg opened this issue · comments
hellow,In SSP method, i know that we can get a result by using cutpursuit to oversegment eval-set's embedding vector.but how to generate the embedding vector of training-set?just use the same network to generate? Looking forward to your replies,thank you very much
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.