US 12,229,993 B2
Automated determination of a canonical pose of a 3D objects and superimposition of 3D objects using deep learning
Frank Theodorus Catharina Claessen, Amsterdam (NL); David Anssari Moin, Amsterdam (NL); and Teo Cherici, Amsterdam (NL)
Assigned to PROMATON HOLDING B.V., Amsterdam (NL)
Appl. No. 17/257,481
Filed by Promaton Holding B.V., Amsterdam (NL)
PCT Filed Jul. 3, 2019, PCT No. PCT/EP2019/067905
§ 371(c)(1), (2) Date Dec. 31, 2020,
PCT Pub. No. WO2020/007941, PCT Pub. Date Jan. 9, 2020.
Claims priority of application No. 18181421 (EP), filed on Jul. 3, 2018.
Prior Publication US 2021/0174543 A1, Jun. 10, 2021
Int. Cl. G06T 7/73 (2017.01); A61C 9/00 (2006.01); G06T 17/20 (2006.01); G06T 19/20 (2011.01)
CPC G06T 7/75 (2017.01) [A61C 9/004 (2013.01); G06T 17/20 (2013.01); G06T 19/20 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30036 (2013.01); G06T 2210/41 (2013.01); G06T 2219/2004 (2013.01); G06T 2219/2016 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for automatically determining a canonical pose of a 3D dental structure represented by data points of a 3D data set, the method comprising:
providing one or more blocks of data points of the 3D data set associated with a first 3D coordinate system to an input of a first 3D deep neural network, the 3D data set representing a 3D dental structure comprising one or more dental features having a first orientation in a 3D space defined by axes of a first 3D coordinate system, the first 3D deep neural network being trained to generate canonical pose information associated with a 3D space defined by axes of a 3D canonical coordinate system relative to a position of part of the 3D dental structure, the orientation of the one or more dental features in the 3D space of the canonical coordinate system being in alignment with the axes of the 3D canonical coordinate system;
receiving canonical pose information from an output of the first 3D deep neural network, the canonical pose information comprising for each data point of the one or more blocks a prediction of a position of the data point in the canonical coordinate system, the position of the data point being defined by canonical coordinates;
using the canonical coordinates to determine an orientation and scaling of the axes of the 3D canonical coordinate system and a position of an origin of the 3D canonical coordinate system relative to the axes and an origin of the first 3D coordinate system and using the orientation, the scaling, and the position to determine transformation parameters, including rotation, translation, and/or scaling parameters, for transforming coordinates of the first 3D coordinate system into canonical coordinates of the 3D canonical coordinate system; and
determining a canonical representation of the 3D dental structure in which the one or more dental features of the 3D dental structure are in alignment with the axes of the 3D canonical coordinate system, the determining of the canonical representation including applying the transformation parameters to coordinates of the data points of the 3D data set.