Back to results
US 10,503,963 B2Granted
System and method for image capture and modeling
AssigneeTake-Two Interactive Software, Inc.
InventorsTimothy L. Meekins, Emre H. Yilmaz
Life of this patent
Estimating the term…
Abstract
A system and method for capturing a player's likeness on an in game model at runtime including geometry and texture.
Claims19
A computer-implemented method for capturing a user's likeness on an in game model at runtime based on a set of images of the user, comprising:
- isolating one or more features from the set of images to be matched, wherein each feature represents a group of pixels that can be found across at least one of the set of images;
- matching a selected feature to said one or more isolated features;
- generating a Fundamental Matrix for each image pair in the acquired set of images based on said matched features;
- triangulating points of the set of images in a three-dimensional space based on said Fundamental Matrix;
- aligning the triangulated points to a target model;
- and
- generating texture for use on the aligned points to generate a first in game model at runtime.
4 more elements
A system for capturing a user's likeness on an in game model at runtime based on a set of images of the user, comprising:
- a database for maintaining the set of images of the user;
- a platform being coupled to said database that executes a set of instructions stored on a non-transitory computer readable medium on the platform and executable by a data processor to cause the data processor to perform operations comprising:
- isolating one or more features from the set of images to be matched, wherein each feature represents a group of pixels that can be found across at least one of the set of images;
- matching a selected feature to said one or more isolated features;
- triangulating points of the set of images in a three-dimensional space based on said matched features;
- aligning the triangulated points to a target model;
- generating texture for use on the aligned points to generate a first in game model at runtime;
- and
- post-processing the aligned points on the first in game model.
6 more elements
A computer-implemented method for capturing a user's likeness on an in game model at runtime based on a set of images of the user, comprising:
- isolating one or more features from the set of images based on computer vision feature detection to obtain at least one feature descriptor, wherein a selected feature of a selected feature descriptor represents a group of pixels that can be found across at least one of the set of images;
- matching a first feature of a selected image to said one or more isolated features to generate a Fundamental Matrix for each image pair in the set of images;
- triangulating points of the set of images in a three-dimensional space based on the matched features and the Fundamental Matrix;
- aligning the triangulated points to a target model based on at least one of robust alignment, coarse alignment, and an Iterative Closest Point translation;
- and
- generating texture for use on the aligned points to generate a first in game model at runtime.
3 more elements
Dependencies are inferred from the claim text.