US 12,462,516 B2
Methods of estimating a bare body shape from a concealed scan of the body
Pengpeng Hu, Ixelles (BE); Adrian Munteanu, Overijse (BE); Nourbakhsh Nastaran, Auderghem (BE); and Stephan Sturges, Brussels (BE)
Assigned to VRIJE UNIVERSITEIT BRUSSEL, Brussels (BE); and Treedy's SPRL, Brussels (BE)
Filed by VRIJE UNIVERSITEIT BRUSSEL, Brussels (BE); and Treedy's SPRL, Brussels (BE)
Filed on Feb. 27, 2024, as Appl. No. 18/588,399.
Application 18/588,399 is a continuation of application No. 17/626,793, granted, now 11,922,593, previously published as PCT/EP2020/069611, filed on Jul. 10, 2020.
Claims priority of application No. 19186137 (EP), filed on Jul. 12, 2019.
Prior Publication US 2024/0193899 A1, Jun. 13, 2024
Int. Cl. G06T 19/20 (2011.01); G06N 3/08 (2023.01); G06T 13/40 (2011.01)
CPC G06T 19/20 (2013.01) [G06N 3/08 (2013.01); G06T 13/40 (2013.01); G06T 2210/16 (2013.01); G06T 2219/2004 (2013.01); G06T 2219/2021 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method of estimating a bare shape from a physical concealed shape of a body, the method comprising:
generating a first dataset comprising a plurality of first surface representations representative of a plurality of bare shapes of a plurality of bodies;
virtually concealing the plurality of bare shapes to obtain a plurality of simulated concealed shapes of the plurality of bodies;
applying the plurality of simulated concealed shapes to a scanning simulator, the scanning simulator generating a second dataset comprising a plurality of second surface representations representative of the plurality of simulated concealed shapes;
applying the first dataset and the second dataset to a neural network, wherein the first dataset is considered as a ground truth dataset to train the neural network;
imaging the physical concealed shape with at least one camera device and generating a third surface representation representative of the physical concealed shape, wherein the third surface representation comprises a three-dimensional point cloud; and
applying the third surface representation to the neural network, the neural network outputting a fourth surface representation representative of an estimated bare shape of the body.