- Number
- 12277662
- Published
- 2025-04-15
- Filed
- 2022-10-31
- Assignee
- PIXAR
- Inventors
- Riemenschneider; Hayko et al.
- CPC
- G06T13/20; G06T7/33; G06V40/10; G06V10/44; G06V10/7715; G06T7/50; G06V10/82; G06T19/20; G06V10/764
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Object-alignment technique for animation (Pixar, granted).
Abstract
Techniques for aligning object representations for animation include analyzing a source object representation and a target object representation to identify a category of the source object and a category of the target object. Based on the category or categories of the objects, a feature extraction machine learning models is selected. The source object representation and the target object representation are provided as input to the selected feature extraction machine learning model to generate respective semantic descriptors and shape vectors for the source and target objects. Based on the semantic descriptors and the shape vectors for the source and target objects, an alignment machine learning model generates an aligned target object representation that is aligned with the source object representation and usable for animating the target object.
Background
BACKGROUND (1) This disclosure relates to computer animation and computer-generated imagery. More specifically, this disclosure is related to techniques for automatically transferring information from one computer model to another. (2) With the wide-spread availability of computers, animators and computer graphics artists can rely upon computers to assist in the animation and computer-generated imagery (CGI) process. This may include using computers to have physical models be represented by virtual models in computer memory. This may also include using computers to facilitate animation, for example, by the designing, posing, deforming, coloring, painting, or the like, of characters or other elements of a computer animation display. (3) The production of animated features and CGI may involve the extensive use of computer graphics techniques to produce a visually appealing image from the geometric description of an object or model that can be used to convey an element of a story. One of the challenges in creating models for use in animated features can be balancing the desire for a visually appealing image of a character or other object with the practical issues involved in allocating the computational resources required to produce those visually appealing images. Often the geometric descriptions of objects or models at various stages in a feature film production environment may be rough and coarse, lacking the realism and detail that would be expected of the final production.
Claims
1. A method for aligning objects for computer generated imagery, the method comprising performing, by a computer system: obtaining a source object representation representing a source object and a target object representation representing a target object; identifying a category of the source object and a category of the target object, wherein identifying the category of the source object and identifying the category of the target object comprises providing the object representations to a classifier machine learning model, wherein the classifier machine learning model is a neural network comprising: an input layer for accepting an object representation corresponding to an object; two or more mixed diffusion and convolution layers; and an output layer for outputting a probability that the object is part of a particular category of objects; based on the category of the source object and the category of the target object, selecting a feature extraction machine learning model from a set of feature extraction machine learning models for different object categories; providing the source object representation and the target object representation as input to the selected feature extraction machine learning model; generating, by the feature extraction machine learning model, information identifying parts of the source object, information identifying parts of the target object, a shape vector for the source object, and a shape vector for the target object; and generating an aligned target object representation that is aligned with the source object representation and usable for animating the target object, the generating using an alignment machine learning model based on the information identifying parts of the source object, the information identifying parts of the target object, the shape vector for the source object, and the shape vector for the target object. ||
10. A system for aligning objects for computer generated imagery, the system comprising one or more processors configured to: obtain a source object representation representing a source object and a target object representation representing a target object; identify a category of the source object and a category of the target object, wherein identifying the category of the source object and identifying the category of the target object comprises providing the object representations to a classifier machine learning model, wherein the classifier machine learning model is a neural network comprising: an input layer for accepting an object representation corresponding to an object; two or more mixed diffusion and convolution layers; and an output layer for outputting a probability that the object is part of a particular category of objects; based on the category of the source object and the category of the target object, select a feature extraction machine learning model from a set of feature extraction machine learning models for different object categories; provide the source object representation and the target object representation as input to the selected feature extraction machine learning model; generate, by the feature extraction machine learning model, information identifying parts of the source object, information identifying parts of the target object, a shape vector for the source object, and a shape vector for the target object; and generate an aligned target object representation that is aligned with the source object representation and usable for animating the target object, the generating using an alignment machine learning model based on the information identifying parts of the source object, the information identifying parts of the target object, the shape vector for the source object, and the shape vector for the target object.