Methods of estimating a bare body shape from a concealed scan of the body
Methods are disclosed for generating a training dataset of concealed shapes and corresponding unveiled shapes of a body for training a neural network. These methods may include generating with the aid of computing means a first dataset comprising a plurality of first surface representations representative of a plurality of bare shapes of a plurality of bodies. The plurality of bare shapes are concealed virtually by means of a computer implemented program in order to obtain a plurality of simulated concealed shapes of the plurality of bodies. The plurality of simulated concealed shapes are applied 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.
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.
2 . The method of claim 1 , wherein the scanning simulator implements a noise model, wherein the noise model adds simulated noise to the plurality of second surface representations, wherein the noise model is representative of a noise signature associated with a three dimensional camera device.
3 . The method of claim 1 , wherein the first surface representations are representative of a plurality of bare shapes assuming a plurality of poses, wherein the neural network outputs the fourth surface representation in substantially a same pose as a pose of the third surface representation.
4 . The method of claim 1 , wherein imaging the physical concealed shape comprises capturing images of the physical concealed shape from multiple points of view.
5 . The method of claim 1 , wherein imaging the physical concealed shape comprises obtaining depth information of the physical concealed shape and wherein the third surface representation is generated based on the depth information.
6 . The method of claim 1 , wherein the physical concealed shape is a dressed human body.
7 . A system, comprising:
a computer implemented with a neural network trained by generating a training dataset of concealed shapes and corresponding bare shapes,
wherein the generating the training dataset comprises:
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, and
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, and
wherein training the neural network comprises applying the first dataset and the second dataset to the neural network, wherein the first dataset is considered as a ground truth dataset; and
at least one camera device operably coupled to the neural network;
wherein the at least one camera device is configured to capture at least one image a physical concealed shape and feed the at least one image to the computer;
wherein the computer is configured to:
generate a third surface representation representative of the physical concealed shape from the at least one image, wherein the third surface representation comprises a three-dimensional point cloud, and
apply the third surface representation to the neural network, the neural network outputting a fourth surface representation representative of an estimated bare shape of the physical concealed shape.
8 . The system of claim 7 , wherein the neural network is further trained by generating confidence level values associated with nodes of the plurality of second surface representations, and the confidence level values are fed as input to the neural network.
9 . The system of claim 7 , wherein the at least one camera device is configured to capture images of the physical concealed shape from multiple points of view.
10 . The system of claim 7 , configured to obtain depth information of the physical concealed shape from the at least one image.
11 . The system of claim 7 , wherein the physical concealed shape is a dressed human body and the estimated bare shape is an undressed human body.