Do I need to recreate PST for my own data?

[pandahops1]

In the paper you mentioned:

PST is a set of particles pre-sampled uniformly within the unit sphere in the 6D space of camera pose. Through moving and rescaling the pre-sampled PST guided by swarm intelligence, our method is able to drive tens of thousands of particles to locate and cover a good local optimum extremely fast and robustly.

It seems that the .tiff files are just a uniform sampling of poses in 6D space. But in readme.md you said:

You can find the .tiff images in PST dicrectory, and please replace the PST path in controller_config.yaml with your own path.

Shoud I create my own PST? Thanks.

[pandahops1]

#10 ok it seems like its answered here.

[xiaopeige]

How to generate PST, I don't know how to generate，，thank you

[jzhzhang]

@xiaopeige
We use the Poisson-disk sampling to generate the PST within a unit sphere. And the particles within the PST range from -1 to 1.

You can adapt to other uniform sampling strategies for simplification, like FPS or voxel sampling.

[xiaopeige]

@xiaopeige We use the Poisson-disk sampling to generate the PST within a unit sphere. And the particles within the PST range from -1 to 1.

You can adapt to other uniform sampling strategies for simplification, like FPS or voxel sampling.

Sorry, I still don't know how to generate PST, do you have relevant examples or references? thank you

[tangqi1012]

@xiaopeige We use the Poisson-disk sampling to generate the PST within a unit sphere. And the particles within the PST range from -1 to 1.
You can adapt to other uniform sampling strategies for simplification, like FPS or voxel sampling.

Sorry, I still don't know how to generate PST, do you have relevant examples or references? thank you

Hello, do you know how to generate PST now？