Cleaned ShapeNet and simulated pressure Dataset

[asadabbas09]

Thanks for awesome work.

As mentioned in the paper, do you guys still have plans to make both the cleaned car split of ShapeNet and the simulated pressure values publicly available?

Thanks

[aluo-x]

Just a heads up. Using this repo With this command: mesh_to_sdf.sample_sdf_near_surface(mesh, number_of_points = 500000, surface_point_method='scan', sign_method='normal', scan_count=100, scan_resolution=400, sample_point_count=10000000, normal_sample_count=11, min_size=0) I recommend sign_method set to sign_method="depth" first with min_size=0.01, and if that raises an error on a mesh, then attempt sign_method="normal" with min_size=0.01. The depth method is robust to incorrectly oriented faces, while normal is robust to holes in the mesh. The car class is especially tricky, as many of the meshes are not water tight.

I'm working on a repo that should be more robust than using either method, but will likely take a while till release.

edit: typo