Issues on point to mesh conversion

[chenweikai]

Hi @jchibane ,

Thanks for sharing the amazing work!

We are trying to convert the generated point clouds (under the folder experiments/shapenet_cars_pretrained/evaluation/generation/) to mesh using the ball pivoting algorithm. However, we found that it is very difficult to obtain high-quality meshing results. We use the ball pivoting algorithm provided by MeshLab. When the radius is large, e.g. 0.05, the reconstructed mesh is incomplete. However, if a small radius, e.g. 0.01, is used, though the reconstructed surface is more complete, there exist a lot of artifacts and the surface normals are not consistent.
The results are shown below:

Reconstruction result using radius = 0.05

Reconstruction result using radius = 0.01

Could you provide more details on how you generate mesh from the point cloud? Or could you share your code of point-to-mesh conversion?
Since we are trying to compare your work in our paper, we would like to ensure our comparison is fair.

Thank you for your response in advance!

[miraymen]

Hi

We used this meshlab .mlx script for converting pointclouds to meshes

<!DOCTYPE FilterScript>
<FilterScript>
 <filter name="Surface Reconstruction: Ball Pivoting">
  <Param type="RichAbsPerc" value="0.005" min="0" name="BallRadius" max="1.15209"/>
  <Param type="RichFloat" value="20" name="Clustering"/>
  <Param type="RichFloat" value="90" name="CreaseThr"/>
  <Param type="RichBool" value="false" name="DeleteFaces"/>
 </filter>
 <filter name="Close Holes">
  <Param type="RichInt" value="30" name="MaxHoleSize"/>
  <Param type="RichBool" value="false" name="Selected"/>
  <Param type="RichBool" value="true" name="NewFaceSelected"/>
  <Param type="RichBool" value="true" name="SelfIntersection"/>
 </filter>
 <filter name="Recompute Vertex Normals">
  <Param enum_val0="None (avg)" enum_val1="By Angle" enum_cardinality="4" enum_val2="By Area" enum_val3="As defined by N. Max" type="RichEnum" value="0" name="weightMode"/>
 </filter>
</FilterScript>

Please try to see if it resolves your problems

[jianglongye]

Is this script too slow? It seems that for the generated point cloud, even if we downsample it to 200k points. It still need nearly 30+ mins to finish the conversion on my macbook. Is it expected?