search

daerduoCarey / structurenet

StructureNet: Hierarchical Graph Networks for 3D Shape Generation
https://cs.stanford.edu/~kaichun/structurenet/
Other
258 stars 45 forks source link

Codes for Point Cloud Abstraction #1

Closed Dustinpro closed 5 years ago

Dustinpro commented 5 years ago

As stated in section 6.4 of StructureNet paper, it trains another PointNet++-based encoder to encode point clouds, which shows the strength of latent space. Could you please provide codes and brief network design for this part (point cloud abstraction)? Thanks! @daerduoCarey

daerduoCarey commented 5 years ago

It's just a straight-forward PointNet++ to extract point cloud global features. Since we have the ground-truth PartNet data, we can directly regress the global feature to the learned StructureNet AE embedding. We pre-train and fix the StructureNet AE network. Then, for each shape in PartNet, we regress the PointNet++ global shape feature to the AE bottleneck feature.

Dustinpro commented 5 years ago

Thank you!