Techniques for generating visualizations of geometric style gradients

Abstract

In various embodiments, a style comparison application generates visualization(s) of geometric style gradient(s). The style comparison application generates a first set of style signals based on a first 3D CAD object and generates a second set of style signals based on a second 3D CAD object. Based on the first and second sets of style signals, the style comparison application computes a different partial derivative of a style comparison metric for each position included in a set of positions associated with the first 3D CAD object to generate a geometric style gradient. The style comparison application generates a graphical element based on at least one of the direction or the magnitude of a vector in the geometric style gradient and positions the graphical element relative to a graphical representation of the first 3D CAD object within a graphical user interface to generate a visualization of the geometric style gradient.

What is claimed is: 
     
         1 . A computer-implemented method for generating one or more visualizations of at least one geometric style gradient, the method comprising:
 generating a first plurality of style signals based on a first three dimensional (3D) computer-aided design (CAD) object;   generating a second plurality of style signals based on a second 3D CAD object;   computing, based on the first plurality of style signals and the second plurality of style signals, a different partial derivative of a style comparison metric for each position included in a first plurality of positions associated with the first 3D CAD object to generate a first geometric style gradient;   generating a first graphical element based on at least one of the direction or the magnitude of a first vector included in the first geometric style gradient; and   positioning the first graphical element relative to a first graphical representation of the first 3D CAD object within a graphical user interface to generate a first visualization of the first geometric style gradient.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising executing a trained neural network at least once to map the first 3D CAD object to a first feature map set. 
     
     
         3 . The computer-implemented method of  claim 2 , wherein a first feature map included in the first feature map set has a plurality of activations associated with a same layer of the trained neural network. 
     
     
         4 . The computer-implemented method of  claim 2 , wherein generating the first plurality of style signals comprises extracting second-order activation information from one or more feature maps included in the first feature map set. 
     
     
         5 . The computer-implemented method of  claim 2 , further comprising executing the trained neural network at least once to map the second 3D CAD object to a second feature map set. 
     
     
         6 . The computer-implemented method of  claim 5 , wherein generating the second plurality of style signals comprises extracting second-order activation information from one or more feature maps included in the second feature map set. 
     
     
         7 . The computer-implemented method of  claim 5 , wherein computing the different partial derivatives of the style comparison metric is further based on the first feature map set and the second feature map set. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein each position included in the first plurality of positions comprises an absolute 3D position in a geometric domain and corresponds to a different sample point in a UV domain. 
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 computing, based on the first plurality of style signals and the second plurality of style signals, a different partial derivative of the style comparison metric for each position included in a second plurality of positions associated with the second 3D CAD object to generate a second geometric style gradient; and   displaying one or more aspects of the second geometric style gradient via the graphical user interface.   
     
     
         10 . The computer-implemented method of  claim 1 , wherein the first graphical element comprise an arrow or a line that is centered at an absolute 3D position corresponding to a UV sample point. 
     
     
         11 . One or more non-transitory computer readable media including instructions that, when executed by one or more processors, cause the one or more processors to generate one or more visualizations of at least one geometric style gradient by performing the steps of:
 generating a first plurality of style signals based on a first three dimensional (3D) computer-aided design (CAD) object;   generating a second plurality of style signals based on a second 3D CAD object;   computing, based on the first plurality of style signals and the second plurality of style signals, a different partial derivative of a style comparison metric for each position included in a first plurality of positions associated with the first 3D CAD object to generate a first geometric style gradient;   generating a first graphical element based on at least one of the direction or the magnitude of a first vector included in the first geometric style gradient; and   positioning the first graphical element relative to a first graphical representation of the first 3D CAD object within a graphical user interface to generate a first visualization of the first geometric style gradient.   
     
     
         12 . The one or more non-transitory computer readable media of  claim 11 , further comprising executing a trained neural network at least once to map the first 3D CAD object to a first feature map set. 
     
     
         13 . The one or more non-transitory computer readable media of  claim 12 , wherein generating the first plurality of style signals comprises extracting second-order activation information from one or more feature maps included in the first feature map set. 
     
     
         14 . The one or more non-transitory computer readable media of  claim 12 , further comprising executing the trained neural network at least once to map the second 3D CAD object to a second feature map set. 
     
     
         15 . The one or more non-transitory computer readable media of  claim 12 , wherein computing the different partial derivatives of the style comparison metric comprises performing one or more backpropagation operations via the trained neural network. 
     
     
         16 . The one or more non-transitory computer readable media of  claim 12 , wherein computing the different partial derivatives of the style comparison metric comprises performing one or more backpropagation operations via the trained neural network. 
     
     
         17 . The one or more non-transitory computer readable media of  claim 11 , wherein the first graphical element points in a direction in which to move a UV sample point to increase a geometric style similarity between the first 3D CAD object and the second 3D CAD object. 
     
     
         18 . The one or more non-transitory computer readable media of  claim 11 , wherein the style comparison metric comprises a similarity metric or a distance metric. 
     
     
         19 . The one or more non-transitory computer readable media of  claim 11 , wherein a representation of the first 3D CAD object comprises a boundary representation (B-rep), a 3D point cloud, or a 3D mesh. 
     
     
         20 . A system comprising:
 one or more memories storing instructions; and   one or more processors coupled to the one or more memories that, when executing the instructions, perform the steps of:
 generating a first plurality of style signals based on a first three dimensional (3D) computer-aided design (CAD) object; 
 generating a second plurality of style signals based on a second 3D CAD object; 
 computing, based on the first plurality of style signals and the second plurality of style signals, a different partial derivative of a style comparison metric for each position included in a first plurality of positions associated with the first 3D CAD object to generate a first geometric style gradient; 
 generating a first graphical element based on at least one of the direction or the magnitude of a first vector included in the first geometric style gradient; and 
 positioning the first graphical element relative to a first graphical representation of the first 3D CAD object within a graphical user interface to generate a first visualization of the first geometric style gradient.