公开(公告)号：US11308669B1

公开(公告)日：2022-04-19

申请号：US17007673

申请日：2020-08-31

Applicant: Apple Inc.

Inventor： Shem Nguyen ,  Austin Caleb Germer

IPC: G06T11/40 ,  G06T7/507 ,  G06T11/00

Abstract: A device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. The device performs a method that includes detecting, in a set of one or more images, appearance features that define an appearance of an object represented in the set of one or more images. The appearance includes one or more shading effects associated with the object. The method includes generating a feature map for the object that encodes the detected appearance features of the object. The method includes displaying, based on the feature map, a computer-generated graphical object with one or more simulated shading effects that are within a degree of similarity to the one or more shading effects associated with the object.

公开(公告)号：US12056581B1

公开(公告)日：2024-08-06

申请号：US16786097

申请日：2020-02-10

Applicant: Apple Inc.

Inventor： Novaira Masood ,  Bo Morgan ,  Shem Nguyen ,  Mark E. Drummond

IPC: G06N20/00 ,  G06N3/006 ,  G06N5/022 ,  G06N5/04 ,  G06N7/01

CPC classification number: G06N20/00 ,  G06N3/006 ,  G06N5/022 ,  G06N5/04 ,  G06N7/01

Abstract: Various implementations disclosed herein include devices, systems, and methods for training of an action determining component of a computer character. In some implementations, actions are taken by the character in a 3D environment according to an action determining component of the character, where the character is rewarded or penalized for interactions associated with an object/concept in the 3D environment according to an assigned object/concept reward or penalty. In some implementations, the reward or the penalty assigned to the object/concept is modified, and the character is then rewarded or penalized for interactions associated with the object/concept according to the modified reward or the modified penalty. The action determining component of the character is trained using a reinforcement learning technique that accounts for rewards or penalties obtained by virtual character for interactions associated with the object/concept.

公开(公告)号：US20230394772A1

公开(公告)日：2023-12-07

申请号：US18204065

申请日：2023-05-31

Applicant: Apple Inc.

Inventor： Bradley W. Peebler ,  Zachary Z. Becker ,  Qiujie Wu ,  Shem Nguyen ,  Sneha S. Bhakare

IPC: G06T19/00 ,  H04N23/63 ,  H04N23/60

CPC classification number: G06T19/006 ,  H04N23/64 ,  H04N23/631

Abstract: Various implementations disclosed herein include devices, systems, and methods for displaying a visual indicator for capturing images. In some implementations, a device includes a display, an environmental sensor, a non-transitory memory, and one or more processors coupled with the display, the environmental sensor and the non-transitory memory. In various implementations, a method includes obtaining a request to capture a sequence of images depicting a subject. The sequence of images is to be captured while an image sensor is being moved along a path with a predefined shape. The method includes determining a dimension of the path. The method includes overlaying, on a pass-through of the physical environment, a virtual indicator that indicates the path with the dimension and the predefined shape. The virtual indicator guides a user of the device along the path while capturing the sequence of the images with the image sensor.

公开(公告)号：US20230396874A1

公开(公告)日：2023-12-07

申请号：US18204072

申请日：2023-05-31

Applicant: Apple Inc.

Inventor： Bradley W. Peebler ,  Zachary Z. Becker ,  Qiujie Wu ,  Shem Nguyen ,  Sneha S. Bhakare

IPC: H04N23/60 ,  H04N23/63

CPC classification number: H04N23/64 ,  H04N23/635 ,  H04N23/631

Abstract: A first device includes a display, an input device, a non-transitory memory and one or more processors coupled with the display, the input device and the non-transitory memory. In some implementations, a method includes detecting, via the input device, an input that corresponds to a request to generate a path for an entity to follow while a sequence of images is to be captured. In some implementations, the method includes generating the path for the entity based on the request. In some implementations, the method includes triggering a second device that is associated with the entity to overlay a virtual indicator indicative of the path on a pass-through of a physical environment. In some implementations, the virtual indicator guides the entity along the path while the sequence of images is captured.

公开(公告)号：US11182980B1

公开(公告)日：2021-11-23

申请号：US17169988

申请日：2021-02-08

Applicant: Apple Inc.

Inventor： Shem Nguyen ,  Arnold Henry Cachelin ,  Novaira Masood ,  Eric John Geusz ,  Pravalika Avvaru

IPC: G09G5/00 ,  G06T19/20 ,  G06T19/00

Abstract: Various implementations disclosed herein include devices, systems, and methods for identifying virtual object kits that may be used to generate a target virtual object. In some implementations, a method includes obtaining a plurality of virtual object kits that generate variations of respective virtual object types. Each virtual object kit is associated with a characteristic parameter. For each virtual object kit, a subset of possible virtual object variations of the virtual object type is generated by assigning corresponding values to the characteristic parameter based on a distribution criterion. A subset of the plurality of virtual object kits is identified based on the target virtual object being within a similarity threshold of one or more virtual object variations generated using the subset of the plurality of virtual object kits in response to a request to assemble a target virtual object.