search

nickgkan / 3d_diffuser_actor

Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"
https://3d-diffuser-actor.github.io/
MIT License
197 stars 24 forks source link

Question about farthest point sampling #63

Open mumianyuxin opened 3 days ago

mumianyuxin commented 3 days ago

Thanks a lot for your work. When I read the source code, I found that the operation of the farthest point sampling is directly based on visual feature tokens. My confusion is why use visual features to compute distance instead of point clouds, is that any benefit?

nickgkan commented 9 hours ago

Hi, We haven't ablated this choice recently. Our idea was that background features would be similar to each other and FPS would keep only a small portion of them.