search

OpenRobotLab / PointLLM

[ECCV 2024] PointLLM: Empowering Large Language Models to Understand Point Clouds
https://runsenxu.com/projects/PointLLM
450 stars 22 forks source link

Scene Understanding #20

Closed LilRedWu closed 5 months ago

LilRedWu commented 5 months ago

Thanks for your excellent job! In the paper，you mentioned the pointLLM scence and showed its capability of scene understanding. I am wondering which checkpoints correspond to the scene model?

RunsenXu commented 5 months ago

Hi, which parts of the paper are you mentioning? We haven't released the scene model at the moment and all experiments in the paper are based on object point clouds (though these models can accept scene-level point clouds and generate outputs).