You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for sharing this amazing work!
Manifold is a wonderful tool for fixing non-manifold mesh and ManifoldPlus is even better!
However, when we were trying to process ShapeNet meshes using ManifoldPlus, we found that though the sharp features are preserved much better than Manifold, the self-intersecting issues still remain in the output mesh. And it happens in almost every mesh in the car category.
For instance, the following shows the processed result using depth = 8:
The self-intersected triangles are highlighted in red:
The input mesh id is 1a56d596c77ad5936fa87a658faf1d26 under car category (02958343).
Since Shapenet is the most comprehensive and influential 3D dataset in the world, we sincerely hope this issue can be fixed so that ManofoldPlus can be much more impactful and useful in the research community.
Thanks a lot!
The text was updated successfully, but these errors were encountered:
Hi @hjwdzh ,
Thank you for sharing this amazing work!
Manifold is a wonderful tool for fixing non-manifold mesh and ManifoldPlus is even better!
However, when we were trying to process ShapeNet meshes using ManifoldPlus, we found that though the sharp features are preserved much better than Manifold, the self-intersecting issues still remain in the output mesh. And it happens in almost every mesh in the car category.
For instance, the following shows the processed result using depth = 8:
The self-intersected triangles are highlighted in red:
The input mesh id is
1a56d596c77ad5936fa87a658faf1d26
under car category (02958343
).The input mesh can be found here:
https://drive.google.com/file/d/1PQQldcOMT3mNNKsaVxTyM2oWePl_2XNy/view?usp=sharing
The output mesh is here:
https://drive.google.com/file/d/1ySplYD6FA3uERTJfmBCxT4-15HChT865/view?usp=sharing
Since Shapenet is the most comprehensive and influential 3D dataset in the world, we sincerely hope this issue can be fixed so that ManofoldPlus can be much more impactful and useful in the research community.
Thanks a lot!
The text was updated successfully, but these errors were encountered: