Struggling to create a suitable watertight mesh using Open3D from point cloud data

[conorssmith]

Hi there, I am trying to create a watertight mesh out of point cloud representing organ contour data from cone beam CT images. My goal is to take two meshes and calculate the volume of intersection between the two of them.

I have tried using each of the methods shown here

Poisson Reconstruction

point_cloud = np.genfromtxt('ct_prostate_contour_data.csv', delimiter=',')
pcd = o3d.geometry.PointCloud()
pcd.points = o3d.utility.Vector3dVector(point_cloud)
pcd.compute_convex_hull()
pcd.estimate_normals()
pcd.orient_normals_consistent_tangent_plane(10)

mesh = o3d.geometry.TriangleMesh.create_from_point_cloud_poisson(pcd, depth=10, width=0, scale=20, linear_fit=True)[0]
mesh.compute_vertex_normals()
mesh.paint_uniform_color([0.5, 0.5, 0.5])
mesh.remove_degenerate_triangles()
o3d.visualization.draw_geometries([pcd, mesh], mesh_show_back_face=True)

While this method seemingly leads to a watertight mesh to my eye, the result of mesh.is_watertight() is False, however for the Bladder data it returns True. Furthermore, the algorithm extends the mesh above and below the vertical limits of the data. Wile this isn't a deal breaking issue if there were a way to minimize it that would be great.

Ball Pivoting

point_cloud = np.genfromtxt('ct_prostate_contour_data.csv', delimiter=',')
pcd = o3d.geometry.PointCloud()
pcd.points = o3d.utility.Vector3dVector(point_cloud)
pcd.compute_convex_hull()
pcd.estimate_normals()
pcd.orient_normals_consistent_tangent_plane(30)

distances = pcd.compute_nearest_neighbor_distance()
avg_dist = np.mean(distances)
radii = [0.1*avg_dist, 0.5*avg_dist, 1*avg_dist, 2*avg_dist] 
r = o3d.utility.DoubleVector(radii)
rec_mesh = o3d.geometry.TriangleMesh.create_from_point_cloud_ball_pivoting(pcd, r)
o3d.visualization.draw_geometries([pcd, rec_mesh], mesh_show_back_face=True)

This would be my preferred method if I were able to fill the holes as it simply connects vertices without interpolation.

Alpha Shapes

point_cloud = np.genfromtxt('ct_prostate_contour_data.csv', delimiter=',')
pcd = o3d.geometry.PointCloud()
pcd.points = o3d.utility.Vector3dVector(point_cloud)
alpha = 8
tetra_mesh, pt_map = o3d.geometry.TetraMesh.create_from_point_cloud(pcd)
mesh = o3d.geometry.TriangleMesh.create_from_point_cloud_alpha_shape(pcd, alpha, tetra_mesh, pt_map)
mesh.compute_vertex_normals()
mesh.paint_uniform_color([0.5, 0.5, 0.5])
mesh.remove_degenerate_triangles()
o3d.visualization.draw_geometries([pcd, mesh])

The results from this are similar to ball pivoting but worse.

ct_prostate_contour_data.csv
ct_rectum_contour_data.csv
ct_bladder_contour_data.csv

[Z-XQ]

same problem!

input mesh data:

full code:
mesh_t = o3d.t.geometry.TriangleMesh.from_legacy(mesh) # to tensor
assert not mesh_t.to_legacy().is_watertight() # true
filled = mesh_t.fill_holes()
assert filled.to_legacy().is_watertight() # false

the mesh is still not watertight after using fill_holes().

[leolei1113]

Facing the same problem. Can anyone help? All of these 3 surface reconstriction methods fail to present decent results.

[germanros1987]

We are working on this. We will provide a solution asap.

[benjaminum]

Hi,
create_from_point_cloud_poisson() is the best choice for creating watertight meshes.
Unfortunately there is no guarantee that the extracted mesh after optimization is watertight.
Something that can help is to reduce the resolution. Setting depth=9 generates watertight meshes for the 3 point clouds.