search

drprojects / superpoint_transformer

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"
MIT License
546 stars 71 forks source link

Superpoint generation #81

Closed jing-zhao9 closed 5 months ago

jing-zhao9 commented 5 months ago

Hello @drprojects, Can the superpoint generation be replaced with a custom superpoint generation method, and then use your proposed superpoint_transformer for semantic segmentation?

drprojects commented 5 months ago

Yes, you can use another partition strategy. We are biased towards the formulation we peopose in the paper because it offers certain properties we judge desirable:

If you have another partition method, you can use it instead of our cut-pursuit formulation, as long as you express it in the expected format. For that you will need to get familiar with our data formats.

Howecer, note that one of the main contributions of our Superpoint Transformer paper is the design of a hierarchical superpoint partition. So your partition algorithm will also need to be hierarchical. See our ICCV'23 paper for more details.