Displacement maps
Examples of methods for determining displacement maps are described herein. In some examples of the methods, a method includes determining a displacement map for a three-dimensional (3D) object model based on a compensated point cloud. In some examples, the method includes assembling the displacement map on the 3D object model for 3D manufacturing.
1 . A method, comprising:
determining a displacement map by mapping a three-dimensional (3D) object model to a two-dimensional (2D) space based on a compensated point cloud to predict deformation in the 3D object model, wherein the compensated point cloud is generated by applying a machine learning model trained on deformation data of previously manufactured objects to predict deformation in the 3D object model, and wherein mapping the 3D object model to the 2D space comprises assigning a coordinate in the 2D space for each vertex of the 3D object model;
assembling the displacement map on the 3D object model to adjust the 3D object model to compensate for the predicted deformation by mapping the displacement map to the 3D object as a digital texture; and
printing the 3D object model with the digital texture.
2 . The method of claim 1 , further comprising mapping the compensated point cloud to the 2D space to produce a mapped point cloud.
3 . The method of claim 2 , wherein determining the displacement map comprises triangulating points of the mapped point cloud corresponding to a mapped polygon from the 3D object model in the 2D space.
4 . The method of claim 3 , wherein determining the displacement map comprises interpolating the triangulation.
5 . The method of claim 1 , wherein the displacement map comprises a set of polygons, wherein each polygon comprises an interpolation of a set of compensated points of the compensated point cloud.
6 . The method of claim 5 , wherein the interpolation indicates a varying degree of compensation over a corresponding polygon.
7 . The method of claim 1 , wherein mapping the 3D object model to 2D space comprises performing UV projection of the 3D object model into the 2D space.
8 . An apparatus, comprising:
a memory; and
a processor in electronic communication with the memory, wherein the processor is to:
map polygons of a three-dimensional (3D) object model and points of a compensated point cloud to a two-dimensional (2D) space to predict deformation in the 3D object model, wherein the compensated point cloud is generated by applying a machine learning model trained on deformation data of previously manufactured objects to predict deformation in the 3D object model;
determine a displacement for each of the polygons based on the points, wherein the displacements are used to adjust the 3D object model to compensate for the predicted deformation by applying the displacement for each of the polygons as a digital texture to the 3D object model; and
print the 3D object model based on the displacements.
9 . The apparatus of claim 8 , wherein each of the polygons is associated with a subset of the points through a point cloud of the 3D object model.
10 . The apparatus of claim 9 , wherein the processor is to determine each displacement by interpolating each subset of the points associated with each of the polygons.
11 . A non-transitory tangible computer-readable medium storing executable code, comprising:
code to cause a processor to encode a compensated point cloud to a digital texture to predict deformation in a three-dimensional (3D) object model, wherein the compensated point cloud is a mapped point cloud and is generated by applying a machine learning model trained on deformation data of previously manufactured objects to predict deformation in the 3D object model, and wherein the digital texture is determined by mapping the 3D object model to a two-dimensional (2D) space by assigning a coordinate in the 2D space for each vertex of the 3D object model;
code to cause the processor to attach the digital texture to the 3D object model based on the compensated point cloud to adjust the 3D object model to compensate for the predicted deformation; and
code to cause the processor to print the 3D object model with the digital texture.
12 . The computer-readable medium of claim 11 , wherein the code to cause the processor to encode the compensated point cloud comprises:
code to cause the processor to determine a set of triangles within a polygon of the 3D object model, wherein the set of triangles comprises vertices corresponding to points of the compensated point cloud; and
code to cause the processor to interpolate the points based on the set of triangles.
13 . The computer-readable medium of claim 11 , wherein the digital texture comprises a displacement map that is wrapped around the 3D object model.