Virtual object machine learning
AssigneeSnap Inc.
InventorsXuehan Xiong, Zehao Xue
Life of this patent
Estimating the term…
Abstract
A machine learning scheme can be trained on a set of labeled training images of a subject in different poses, with different textures, and with different background environments. The label or marker data of the subject may be stored as metadata to a 3D model of the subject or rendered images of the subject. The machine learning scheme may be implemented as a supervised learning scheme that can automatically identify the labeled data to create a classification model. The classification model can classify a depicted subject in many different environments and arrangements (e.g., poses).
Claims20
A method comprising:
- storing, on a device, a convolutional neural network trained to detect different gestures of different objects, the convolutional neural network trained on a plurality of images generated from three-dimensional models of the different objects, each of the plurality of images depicting a three-dimensional model of one of the different objects in a combination of the different gestures, textures, and three-dimensional environments;
- identifying an image depicting a physical object;
- and
- classifying, using the convolutional neural network operating on one or more processors of the device, the physical object as being in a gesture from the different gestures of the different objects by applying the convolutional neural network to the image depicting the physical object.
A system comprising:
- one or more processors of a machine;
- a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising:
- storing, on a device, a convolutional neural network trained to detect different gestures of different objects, the convolutional neural network trained on a plurality of images generated from three-dimensional models of the different objects, each of the plurality of images depicting a three-dimensional model of one of the different objects in a combination of the different gestures, textures, and three-dimensional environments;
- identifying an image depicting a physical object;
- and
- classifying, using the convolutional neural network operating on one or more processors of the device, the physical object as being in a gesture from the different gestures of the different objects by applying the convolutional neural network to the image depicting the physical object.
A non-transitory machine-readable storage device embodying instructions that, when executed by a machine, cause the machine to perform operations comprising:
- storing, on a device, a convolutional neural network trained to detect different gestures of different objects, the convolutional neural network trained on a plurality of images generated from three-dimensional models of the different objects, each of the plurality of images depicting a three-dimensional model of one of the different objects in a combination of the different gestures, textures, and three-dimensional environments;
- identifying an image depicting a physical object;
- and
- classifying, using the convolutional neural network operating on one or more processors of the machine, the physical object as being in a gesture from the different gestures of the different objects by applying the convolutional neural network to the image depicting the physical object.
Dependencies are inferred from the claim text.