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).
Claims19
A method comprising:
- generating, using one or more processors of a machine, a plurality of images from a three-dimensional (3D) model having markers indicating key points of the 3D model, the plurality of images depicting the 3D model in a plurality of gestures in different 3D environments that curve around the 3D model and reflect virtual light on the 3D model, some of the plurality of images depicting the 3D model differently due to the virtual light of the different 3D environments reflecting differently on the 3D model, the plurality of gestures of the 3D model indicated by arrangements of the markers;
- generating a machine learning model by training a machine learning scheme on the plurality of images;
- identifying an image depicting a physical object;
- and
- classifying, using the machine learning model, the physical object as being in a gesture from the plurality of gestures.
A system comprising:
- one or more processors of a machine;
- and
- a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising:
- generating a plurality of images from a three-dimensional (3D) model having markers indicating key points of the 3D model, the plurality of images depicting the 3D model in a plurality of gestures in different 3D environments that curve around the 3D model and reflect virtual light on the 3D model, some of the plurality of images depicting the 3D model differently due to the virtual light of the different 3D environments reflecting differently on the 3D model, the plurality of gestures of the 3D model indicated by arrangements of the markers;
- generating a machine learning model by training a machine learning scheme on the plurality of images;
- identifying an image depicting a physical object;
- and
- classifying, using the machine learning model, the physical object as being in a gesture from the plurality of gestures.
A non-transitory machine-readable storage device embodying instructions that, when executed by a machine, cause the machine to perform operations comprising:
- generating a plurality of images from a three-dimensional (3D) model having markers indicating key points of the 3D model, the plurality of images depicting the 3D model in a plurality of gestures in different 3D environments that curve around the 3D model and reflect virtual light on the 3D model, some of the plurality of images depicting the 3D model differently due to the virtual light of the different 3D environments reflecting differently on the 3D model, the plurality of gestures of the 3D model indicated by arrangements of the markers;
- generating a machine learning model by training a machine learning scheme on the plurality of images;
- identifying an image depicting a physical object;
- and
- classifying, using the machine learning model, the physical object as being in a gesture from the plurality of gestures.
Dependencies are inferred from the claim text.