US 12,456,256 B2
Method for generating a three-dimensional working surface of a human body, system
Tanguy Serrat, Saint-Cloud (FR); and Ali Khachlouf, Paris (FR)
Assigned to SQUAREMIND, Paris (FR)
Filed by SQUAREMIND, Paris (FR)
Filed on Mar. 1, 2023, as Appl. No. 18/176,733.
Application 18/176,733 is a continuation of application No. 17/438,249, granted, now 11,631,219, previously published as PCT/EP2020/057703, filed on Mar. 19, 2020.
Claims priority of application No. 1902939 (FR), filed on Mar. 21, 2019.
Prior Publication US 2023/0206561 A1, Jun. 29, 2023
Int. Cl. G06T 17/20 (2006.01); G06F 18/214 (2023.01); G06T 3/60 (2006.01); G06T 7/40 (2017.01); G06T 7/50 (2017.01); G06T 7/60 (2017.01); G06T 7/73 (2017.01); G06T 19/20 (2011.01); G06V 10/46 (2022.01); G06V 10/766 (2022.01); G06V 10/82 (2022.01)
CPC G06T 17/20 (2013.01) [G06F 18/214 (2023.01); G06T 3/60 (2013.01); G06T 7/40 (2013.01); G06T 7/50 (2017.01); G06T 7/60 (2013.01); G06T 7/75 (2017.01); G06T 19/20 (2013.01); G06V 10/46 (2022.01); G06V 10/766 (2022.01); G06V 10/82 (2022.01); G06T 2200/08 (2013.01); G06T 2207/10012 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20072 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01); G06T 2210/41 (2013.01); G06T 2219/2016 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for generating a three-dimensional working surface of a human body, the method comprising:
receiving input data corresponding to geometric data;
generating a first point cloud of points from the input data, each point being associated with a three-dimensional spatial coordinate;
generating partial views of parameterised body models corresponding to a parametric body model parameterised with different parameterisation configurations, each one of the parameterised body models being represented by a point cloud so that the parameterised body models are represented by point clouds; wherein the parametric body model models the human body in which a set of articulations are predefined, each parameterisation configuration of the different parameterisation configurations being defined by a set of modelling parameters comprising at least one first angle of rotation of each articulation of the set of articulations and at least one first shape coefficient;
calculating a set of geometric parameters comprising at least one rotation at at least one point of the first point cloud or at at least one articulation of a human body model and at least one shape coefficient by a regression, said regression being carried out from the first point cloud and from a series of matrix operations performed according to different layers of a neural network trained from the partial views, wherein entry parameters of the neural network comprise three dimensional spatial coordinates, and
determining another parameterised model from the set of geometric parameters to generate a body model of the human body comprising a first meshing,
wherein each partial view of the plurality of partial views is generated from a subset of points of one of the point clouds.