Apple Inc.

Other

Behrooz Mahasseni

Mark E Drummond

Siva Chandra Mouli Sivapurapu

Aashi Manglik

Shaun D Budhram

Edward S Ahn

Payal Jotwani

Bo Morgan

Dan Feng

Mu Qiao

Daniel Laszlo Kovacs

Gutemberg B Guerra Filho

Stefan Auer

Michael J Gutensohn

Saumil B Patel

Andreas N Bigontina

Bradley Warren Peebler

Noah Gamboa

Noah Jonathan Gamboa

In some implementations, the method includes: obtaining a plurality of animations; determining initial and end motion states for each of the plurality of animations; generating an animation graph including nodes for each of the plurality of animations by connecting, with a directional edge, a first node with an end motion state to a second node with an initial motion state that matches the end motion state of the first node; generating a transitional animation that is not included among the plurality of animations from an initial reference motion state to a target motion state that corresponds to a path that traverses the animation graph from a third node associated with the initial reference motion state to a fourth node associated with the target motion state; and updating the animation graph by removing one or more nodes from the animation graph based at least in part on the transitional animation.

Method and device for generating an animation graph

In one implementation, a method of composing a scene content is performed at a device including a display, one or more processors, and non-transitory memory. The method includes generating a definition of a scene based on textual or speech input and a model of a physical environment, wherein the definition includes a constraint that defines a spatial relationship between a virtual asset and an anchor asset that corresponds to one or more physical objects in the physical environment. The method includes generating, based on the definition of the scene and the model of the physical environment, a first instance of the scene that satisfies the constraint with the virtual asset in the spatial relationship with a first one of the one or more physical objects in the physical environment. The method includes presenting, on the display, the first instance of the scene.

Methods and systems for composing and executing a scene

In some implementations, a device includes one or more processors and a non-transitory memory. In some implementations, a method includes obtaining an object that includes a plurality of portions including a first portion and a second portion. In some implementations, the method includes determining a first saliency value for the first portion of the object and a second saliency value for the second portion of the object. In some implementations, the method includes triggering presentation of the first portion of the object in accordance with a first display characteristic that is based on the first saliency value and the second portion of the object in accordance with a second display characteristic that is based on the second saliency value.

Triggering presentation of an object based on saliency

In one implementation, a method of displaying content is performed at a device including a display, one or more processors, and non-transitory memory. The method includes scanning a first physical environment to detect a first physical object in the first physical environment and a second physical object in the first physical environment, wherein the first physical object meets at least one first object criterion and the second physical object meets at least one second object criterion. The method includes displaying, in association with the first physical environment, a virtual object moving along a first path from the first physical object to the second physical object. The method includes scanning a second physical environment to detect a third physical object in the second physical environment and a fourth physical object in the second physical environment, wherein the third physical object meets the at least one first object criterion and the fourth physical object meets the at least one second object criterion. The method includes displaying, in association with the second physical environment, the virtual object moving along a second path from the third physical object to the fourth physical object, wherein the second path is different than the first path.

In some implementations, a device includes one or more sensors, one or more processors and a non-transitory memory. In some implementations, a method includes determining that a first portion of a physical environment is associated with a first saliency value and a second portion of the physical environment is associated with a second saliency value that is different from the first saliency value. In some implementations, the method includes obtaining, via the one or more sensors, environmental data corresponding to the physical environment. In some implementations, the method includes generating, based on the environmental data, a model of the physical environment by modeling the first portion with a first set of modeling features that is a function of the first saliency value and modeling the second portion with a second set of modeling features that is a function of the second saliency value.

Modeling a physical environment based on saliency

In one implementation, a method for modeling a behavior with synthetic training data. The method includes: obtaining source content that includes an entity performing one or more actions within an environment; generating a first environment characterization vector characterizing the environment; generating a first set of behavioral trajectories associated with the one or more actions of the entity based on the source content and the first characterization vector for the environment; generating a second environment characterization vector for the environment by perturbing the first environment characterization vector; generating a second set of behavioral trajectories associated with one or more potential actions of the entity based on the source content and the second characterization vector for the environment; and training a behavior model for a virtual agent based on the first and second sets of behavioral trajectories in order to imitate the entity.

Method and device for modeling a behavior with synthetic training data

In one implementation, a method for generating a blended animation. The method includes: obtaining a motion input vector for a current time period; generating a motion output vector and pose information for the current time period based on the motion input vector; selecting an animated motion from a bank of animated motions for the current time period that matches the pose information within a threshold tolerance value; obtaining a blending coefficients vector for the current time period; generating a blended animation for the current time period by blending the motion output vector with the animated motion based on the blending coefficients vector; and generating a reward signal for the blended animation for the current time period.

Method and device for generating a blended animation

In one implementation, a method for inverse reinforcement learning for tailoring virtual agent behaviors to a specific user. The method includes: obtaining an initial behavior model for a virtual agent and an initial state for a virtual environment associated with the virtual agent, wherein the initial behavior model includes one or more tunable parameters; generating, based on the initial behavior model and the initial state for the virtual environment, a first set of behavioral trajectories for the virtual agent; obtaining a second set of behavioral trajectories from a source different from the initial behavior model; and generating an updated behavior model by adjusting at least one of the one or more tunable parameters of the initial behavior model as a function of the first and second sets of behavioral trajectories, wherein at least one of the first and second sets of behavioral trajectories are assigned different weights.

Inverse reinforcement learning for user-specific behaviors

A method includes obtaining a set of images that correspond to a person. The method includes generating a body pose model of the person defined by a branched plurality of neural network systems. Each neural network system models a respective portion of the person between a first body-joint and a second body-joint as dependent on an adjacent portion of the person sharing the first body-joint. Providing the set of images of the respective portion to a first one and a second one of the neural network systems. The first one and second one correspond to adjacent body portions. The method includes determining, jointly by at least the first one and second one of the plurality of neural network systems pose information for the first respective body-joint and the second respective body-joint.

Growing community of inventors

San Jose, CA, United States of America

Behrooz Mahasseni