Methods and systems for using trained generative adversarial networks to impute 3D data for underwriting, claim handling and retail operations
View Patent ↗A method for using a trained generative adversarial network to improve underwriting, claim handling and retail operations includes receiving a 3D point cloud; and generating a gap-filled semantically-segmented 3D point cloud using a trained generative adversarial network. A computing system for using a trained generative adversarial network to improve vehicle orientation and navigation includes one or more processors, and one or more memories having stored thereon computer-executable instructions that, when executed, cause the computing system to: receive a 3D point cloud; and generate a gap-filled semantically-segmented 3D point cloud using the trained generative adversarial network. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed, cause a computer to: receive a 3D point cloud; and generate a gap-filled semantically-segmented 3D point cloud using a trained generative adversarial network.
1 . A computer-implemented method for using a trained generative adversarial network to analyze a structure, the computer-implemented method comprising:
obtaining, by one or more processors, a 3D point cloud of a portion of the structure;
augmenting, by the one or more processors, the 3D point cloud with data describing a characteristic of one or more structural elements represented within the 3D point cloud corresponding to the portion of the structure;
generating, by the one or more processors, a gap-filled semantically segmented 3D point cloud from the 3D point cloud as augmented with the data using the trained generative adversarial network, wherein the trained generative adversarial network fills one or more gaps in the 3D point cloud while generating the gap-filled semantically segmented 3D point cloud; and
outputting, by the one or more processors, a representation of the gap-filled semantically segmented 3D point cloud for presentation to a user.
2 . The computer-implemented method of claim 1 , wherein generating the gap-filled semantically segmented 3D point cloud comprises automatically removing one or more objects from the 3D point cloud to generate the one or more gaps.
3 . The computer-implemented method of claim 2 , wherein the 3D point cloud comprises a semantically segmented 3D point cloud in which the one or more objects are identified as distinct regions.
4 . The computer-implemented method of claim 1 , further comprising:
identifying, by the one or more processors, an aspect of the structure based upon the gap-filled semantically segmented 3D point cloud.
5 . The computer-implemented method of claim 4 , wherein the aspect of the structure comprises a number of windows of the structure, a size of the portion of the structure, a number of stories of the structure, a roof composition of the structure, or a roof type of the structure.
6 . The computer-implemented method of claim 4 , wherein the aspect of the structure comprises an appliance disposed within the structure.
7 . The computer-implemented method of claim 4 , further comprising:
obtaining, by the one or more processors, historical customer data associated with the structure; and
determining, by the one or more processors, a characteristic of the aspect of the structure based upon the historical customer data.
8 . The computer-implemented method of claim 1 , further comprising:
obtaining, by the one or more processors, historical customer data associated with the structure;
comparing, by the one or more processors, the gap-filled semantically segmented 3D point cloud against the historical customer data to detect damage to the structure.
9 . The computer-implemented method of claim 1 , wherein obtaining the 3D point cloud comprises controlling an unmanned aerial vehicle to capture the 3D point cloud as an aerial view of the portion of the structure.
10 . The computer-implemented method of claim 1 , wherein the structure comprises a habitable building.
11 . A computing system for using a trained generative adversarial network to analyze a structure, the computing system comprising:
one or more processors, and
one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to:
obtain a 3D point cloud of a portion of the structure;
augment the 3D point cloud with data describing a characteristic of one or more structural elements represented within the 3D point cloud corresponding to the portion of the structure;
generate a gap-filled semantically segmented 3D point cloud from the 3D point cloud as augmented with the data using the trained generative adversarial network, wherein the trained generative adversarial network fills one or more gaps in the 3D point cloud while generating the gap-filled semantically segmented 3D point cloud; and
output a representation of the gap-filled semantically segmented 3D point cloud for presentation to a user.
12 . The computing system of claim 11 , wherein:
the 3D point cloud comprises a semantically segmented 3D point cloud in which one or more objects are identified as distinct regions; and
the computer-executable instructions that cause the computing system to generate the gap-filled semantically segmented 3D point cloud cause the computing system to automatically remove the one or more objects from the semantically segmented 3D point cloud to generate the one or more gaps.
13 . The computing system of claim 11 , wherein the computer-executable instructions further cause the computing system to:
identify an aspect of the structure based upon the gap-filled semantically segmented 3D point cloud.
14 . The computing system of claim 13 , wherein the aspect of the structure comprises a number of windows of the structure, a size of the portion of the structure, a number of stories of the structure, a roof composition of the structure, or a roof type of the structure.
15 . The computing system of claim 13 , wherein the computer-executable instructions further cause the computing system to:
obtain historical customer data associated with the structure; and
determine a characteristic of the aspect of the structure based upon the historical customer data.
16 . A non-transitory computer-readable medium having stored thereon computer-executable instructions for using a trained generative adversarial network to analyze a structure that, when executed by one or more processors of a computing system, cause the computing system to:
obtain a 3D point cloud of a portion of the structure;
augment the 3D point cloud with data describing a characteristic of one or more structural elements represented within the 3D point cloud corresponding to the portion of the structure;
generate a gap-filled semantically segmented 3D point cloud from the 3D point cloud as augmented with the data using the trained generative adversarial network, wherein the trained generative adversarial network fills one or more gaps in the 3D point cloud while generating the gap-filled semantically segmented 3D point cloud; and
output a representation of the gap-filled semantically segmented 3D point cloud for presentation to a user.
17 . The non-transitory computer-readable medium of claim 16 , wherein:
the 3D point cloud comprises a semantically segmented 3D point cloud in which one or more objects are identified as distinct regions; and
the computer-executable instructions that cause the computing system to generate the gap-filled semantically segmented 3D point cloud cause the computing system to automatically remove the one or more objects from the semantically segmented 3D point cloud to generate the one or more gaps.
18 . The non-transitory computer-readable medium of claim 16 , wherein the computer-executable instructions further cause the computing system to:
identify an aspect of the structure based upon the gap-filled semantically segmented 3D point cloud.
19 . The non-transitory computer-readable medium of claim 18 , wherein the aspect of the structure comprises a number of windows of the structure, a size of the portion of the structure, a number of stories of the structure, a roof composition of the structure, or a roof type of the structure.
20 . The non-transitory computer-readable medium of claim 18 , wherein the computer-executable instructions further cause the computing system to:
obtain historical customer data associated with the structure; and
determine a characteristic of the aspect of the structure based upon the historical customer data.