CPC G06T 7/0004 (2013.01) [G06N 20/00 (2019.01); G06Q 30/0283 (2013.01); G06T 3/18 (2024.01); G06T 7/10 (2017.01); G06T 7/70 (2017.01); G06T 17/00 (2013.01); G06T 2200/24 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30204 (2013.01); G06T 2207/30252 (2013.01)] | 20 Claims |
1. A method comprising:
obtaining an image of a damaged vehicle and a three-dimensional (3D) vehicle model associated with the damaged vehicle;
segmenting the image to identify different portions of the image that capture different parts of the damaged vehicle, wherein segmenting the image comprises generating a first mask associated with the image;
identifying one or more damage markers that indicate damage to the damaged vehicle based on the image, wherein identifying the one or more damage markers comprises generating a second mask associated with the image;
identifying a pose of the damaged vehicle within the image;
identifying differences between contours of at least one of the parts of the damaged vehicle as identified in the first mask and contours of the at least one of the parts as identified in the 3D vehicle model when oriented in the identified pose;
warping the one or more damage markers based on the identified differences to generate one or more transformed damage markers; and
mapping the one or more transformed damage markers onto the 3D vehicle model based on the identified pose, the one or more mapped damage markers identifying one or more locations and dimensions of the damage to the damaged vehicle on the 3D vehicle model.
|