Giters

autonomousvision / shape_as_points

[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

Home Page:https://pengsongyou.github.io/sap

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Input all Points for Optimization-based method?

Runsong123 opened this issue · comments

commented

Hi Songyou,

Thanks for sharing your code for the excellent work!
I am curious about the optimization-based part and I have two questions. Can you help me? thanks a lot in advance. :)

  • Do you use the whole point cloud? For example, the "daratech" shape(SRB dataset) contains 71265 point cloud, you put all the point clouds for your methods or you downsample them first.
  • Can you provide the parameter for Poisson Surface Reconstruction(e.g. depth) and parameter for minimum spanning tree method if possible.

Looking forward to your reply!

Best,
Runsong

commented

Hi @Runsong123 , thanks for your interest in our work. Regarding your questions:

  • We use all points during the optimization, but only use the subsampled points for chamfer loss calculation in each iteration. Check here and here.
  • For sPSR, we use depth=8. For minimum spanning tree algorithm, we use the implementation from Open3D. We set search_param=o3d.geometry.KDTreeSearchParamHybrid(radius=0.1, max_nn=30).

Hope this helps.

Best,
Songyou

commented

Got it! Thanks a lot! :)

Best,
Runsong