Snap Inc. patent applications on September 5th, 2024

Patent Applications by Snap Inc. on September 5th, 2024

Snap Inc.: 11 patent applications

Snap Inc. has applied for patents in the areas of G06T11/00 (3), G06T19/20 (2), H04N7/01 (1), G09G3/36 (1), H04L51/42 (1) G06F3/011 (1), G06F3/04845 (1), G06F9/4881 (1), G06T7/0002 (1), G06T13/80 (1)

With keywords such as: image, prompt, audio, based, device, object, user, images, automated, and methods in patent application abstracts.

Patent Applications by Snap Inc.

20240295918. DISTANCE DETERMINATION FOR MIXED REALITY INTERACTION_simplified_abstract_(snap inc.)

Inventor(s): Benjamin Lucas of San Francisco CA (US) for snap inc.

IPC Code(s): G06F3/01, G06F3/0346, G06F3/04815, G06F3/0482, G06F3/04847

CPC Code(s): G06F3/011

Abstract: systems, methods, and computer readable media that determines distances for mixed reality interaction, where the methods include determining a first position of a point of a surface and rendering a virtual reality (vr) interactive item comprising a vr interactive control. the methods further include tracking a control indicator controlled by the user by determining a first plurality of positions of the control indicator and activating the vr interactive control in response to detecting the control indicator controlled by the user transgressing a first threshold distance from the vr interactive control. the methods further include determining a closest position of the first plurality of positions to the point based on the first position, determining the point of the surface to have a second position based on the determined closest position plus a constant for the control indicator, and associating a second threshold with the point of the surface.

20240295953. PROMPT MODIFICATION FOR AUTOMATED IMAGE GENERATION_simplified_abstract_(snap inc.)

Inventor(s): Aleksandr Zakharov of Dubai (AE) for snap inc., Sergey Smetanin of London (GB) for snap inc., Arnab Ghosh of Oxford (GB) for snap inc., Pavel Savchenkov of London (GB) for snap inc.

IPC Code(s): G06F3/04845, G06T11/00

CPC Code(s): G06F3/04845

Abstract: examples disclosed herein describe prompt modification techniques for automated image generation. an image generation request comprising a base prompt is received from a user device. a plurality of prompt modifiers is identified. a processor-implemented scoring engine determines, for each prompt modifier, a modifier score. the modifier score for each prompt modifier is associated with the base prompt. one or more of the prompt modifiers are automatically selected based on the modifier scores. a modified prompt is generated. the modified prompt is based on the base prompt and the one or more selected prompt modifiers. the modified prompt is provided as input to an automated image generator to generate an image, and the image is caused to be presented on the user device.

20240296066. ASYNCHRONOUS TASK FRAMEWORK_simplified_abstract_(snap inc.)

Inventor(s): Ryan Olson of Seattle WA (US) for snap inc.

IPC Code(s): G06F9/48, G06F9/54

CPC Code(s): G06F9/4881

Abstract: systems, devices, media, and methods are presented that provide an asynchronous task scheduling framework in which tasks are asynchronously scheduled for performance by a server system. scheduling of a task is performed by marshalling the task (units of work converted to bytes) and storing the task in queues and retrieving the task from the queues and unmarshalling the retrieved tasks (bytes to units of work). the unmarshalled task is sent to a service (e.g., an email service) for performance. examples of the approach introduce wrapping a hypertext transfer protocol (http)/remote procedure call (rpc) call and brokering it transparently through a high-throughput message queue system.

20240296535. AUTOMATIC IMAGE QUALITY EVALUATION_simplified_abstract_(snap inc.)

Inventor(s): Mykyta Bakunov of Adliswil (CH) for snap inc., Arnab Ghosh of Oxford (GB) for snap inc., Pavel Savcenkov of London (GB) for snap inc., Sergey Smetanin of London (GB) for snap inc., Jian Ren of Marina Del Ray CA (US) for snap inc.

IPC Code(s): G06T7/00, G06F40/126, G06F40/40, G06T11/00

CPC Code(s): G06T7/0002

Abstract: examples disclosed herein describe techniques for automatic image quality evaluation. a first set of images generated by a first automated image generator and a second set of images generated by a second automated image generator are accessed. a first machine learning model generates a first quality indicator for each image in the first set of images and the second set of images. a second machine learning model generates a second quality indicator for each image in the first set of images and the second set of images. based on the generated indicators, a first image from the first set of images and a second image from the second set of images are automatically selected and compared. a first ranking of the first automated image generator and the second automated image generator is generated based on the comparison, and ranking data is caused to be presented on a device.

20240296614. PHOTOREALISTIC REAL-TIME PORTRAIT ANIMATION_simplified_abstract_(snap inc.)

Inventor(s): Eugene Krokhalev of London (GB) for snap inc., Aleksandr Mashrabov of Los Angeles CA (US) for snap inc., Pavel Savchenkov of London (GB) for snap inc.

IPC Code(s): G06T13/80, G06T7/174, G06V40/16

CPC Code(s): G06T13/80

Abstract: provided are systems and methods for portrait animation. an example method includes receiving, by a computing device, scenario data including information concerning movements of a first head, receiving, by the computing device, a target image including a second head and a background, determining, by the computing device and based on the target image and the information concerning the movements of the first head, two-dimensional (2d) deformations of the second head in the target image, applying, by the computing device, the 2d deformations to the target image to obtain at least one output frame of an output video, the at least one output frame including the second head displaced according to the movements of the first head, and filling, by the computing device and using a background prediction neural network, a portion of the background in gaps between the displaced second head and the background.

20240296640. APPLYING PREGENERATED VIRTUAL EXPERIENCES IN NEW LOCATION_simplified_abstract_(snap inc.)

Inventor(s): Gal Dudovitch of Tel Aviv (IL) for snap inc., Peleg Harel of Ramat Gan (IL) for snap inc., Ma'ayan Mishin Shuvi of Givatayim (IL) for snap inc., Itamar Berger of Hod Hasharon (IL) for snap inc., Avihay Assouline of Tel Aviv (IL) for snap inc.

IPC Code(s): G06T19/00, G06N3/02, G06T19/20

CPC Code(s): G06T19/006

Abstract: aspects of the present disclosure involve a system for providing virtual experiences. the system performs operations including selecting, by a messaging application, a virtual experience that represents a previously captured real-world environment at a first location; accessing an image representing a new real-world environment at a second location, the image depicting a plurality of real-world objects; receiving input that selects a first real-world object from the plurality of real-world objects depicted in the image; and modifying the image, accessed at the second location, based on the virtual experience to depict the previously captured real-world environment with the first real-world object.

20240296645. NEURAL RENDERING USING TRAINED ALBEDO TEXTURES_simplified_abstract_(snap inc.)

Inventor(s): Vladislav Shakhrai of London (GB) for snap inc., Sergey Demyanov of Santa Monica CA (US) for snap inc., Mikhail Vasilkovskii of Playa Vista CA (US) for snap inc., Aleksei Stoliar of Marina del Rey CA (US) for snap inc.

IPC Code(s): G06T19/20, G06T7/40, G06T11/00, G06T17/20

CPC Code(s): G06T19/20

Abstract: methods and systems are disclosed for performing operations for generating a photorealistic rendering of an object. the operations include: accessing a set of albedo textures and a machine learning model associated with a real-world object, the set of albedo textures and a machine learning model having been trained based on a plurality of viewpoints of the real-world object; obtaining a three-dimensional (3d) mesh of the real-world object; receiving input that selects a new viewpoint that differs from the plurality of viewpoints of the real-world object; and generating a photorealistic rendering of the real-world object from the new viewpoint based on the 3d mesh of the real-world object, the set of albedo textures, and the machine learning model associated with the real-world object.

20240296811. PULSE WIDTH MODULATION FOR PHASE-MODULATING DISPLAY_simplified_abstract_(snap inc.)

Inventor(s): Ian Kyles of West Linn OR (US) for snap inc., Howard V. Goetz of Tigard OR (US) for snap inc.

IPC Code(s): G09G3/36

CPC Code(s): G09G3/3696

Abstract: a method is disclosed for controlling a liquid crystal pulse width modulated display. a repetition period includes a group periods, each including b modulation intervals, each modulation interval spanning h unit durations and, except for the final modulation interval of the repetition period, a remainder unit duration. a desired number n of unit duration pulses are distributed into h unit duration pulses for each modulation interval, with remainder desired pulses distributed among the remainder unit durations of the modulation intervals. a drive sequence is generated, including one or more repetitions of the repetition period.

20240297866. RETENTION MODEL MANAGEMENT FOR CHAT CONVERSATIONS_simplified_abstract_(snap inc.)

Inventor(s): Jeremy Voss of Los Angeles CA (US) for snap inc., Jonathan Brody of Marina Del Rey CA (US) for snap inc., Nathan Kenneth Boyd of Los Angeles CA (US) for snap inc.

IPC Code(s): H04L51/42, H04L51/04, H04L51/216, H04L51/52

CPC Code(s): H04L51/42

Abstract: aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for managing chat conversation retention models. the method may include causing display of an interface that enables a user to select one of multiple retention models for association with an electronic chat conversation, and receiving, via the selector interface, a selection of a particular retention model. the retention model specifies an amount of time that each individual message in the electronic chat conversation is accessible upon being read by a receiving user. the method further includes storing a newly received message as part of the chat conversation, where the storing includes configuring a retention duration attribute for the message in accordance with the amount of time specified by the retention model. the method further includes erasing the message in accordance with the retention duration attribute.

20240297957. ASPECT RATIO CONVERSION FOR AUTOMATED IMAGE GENERATION_simplified_abstract_(snap inc.)

Inventor(s): Mykyta Bakunov of Freienbach (CH) for snap inc., Arnab Ghosh of Oxford (GB) for snap inc., Pavel Savchenkov of London (GB) for snap inc., Sergey Smetanin of London (GB) for snap inc., Jian Ren of Marina Del Ray CA (US) for snap inc.

IPC Code(s): H04N7/01, G06T3/40, G06T7/70, G06T9/00, G06V10/25

CPC Code(s): H04N7/0122

Abstract: examples disclosed herein describe aspect ratio conversion techniques for automated image generation. an image generation request comprising a prompt is received from a user device. a processor-implemented automated image generator may generate a first image based on the prompt. the first image has a first aspect ratio. according to some examples, a region of interest is determined in the first image, based on a prompt alignment indicator for the region of interest. the first image is then processed to obtain a second image. the processing includes an automatic cropping operation directed at the region of interest. the second image has a second aspect ratio that is different from the first aspect ratio. the second image is caused to be presented on the user device.

20240298138. LOW LATENCY, LOW POWER MULTI-CHANNEL AUDIO PROCESSING_simplified_abstract_(snap inc.)

Inventor(s): Ashwani Arya of Cypress CA (US) for snap inc., Tejas Bahulkar of Sunnyvale CA (US) for snap inc., Daniel Harris of San Francisco CA (US) for snap inc., Daniel C. Wiggins of Port Hueneme CA (US) for snap inc.

IPC Code(s): H04S7/00, G10L19/008, H04R5/033, H04S3/00

CPC Code(s): H04S7/304

Abstract: an electronic eyewear device includes a display and a speaker system adapted to present augment reality objects and associated sounds in a scene being viewed by the user. a processor receives one or more audio tracks respectively associated with one or more augmented reality objects, encodes the audio tracks into an aggregated audio track including the audio tracks, a header for each audio track that uniquely identifies each respective audio track, and an aggregate header that identifies the number of tracks in the aggregated audio track. the processor transfers the aggregated audio track to an audio processor that uses the header for each audio track and the aggregate header to separate the audio tracks from the aggregated audio track. the audio processor processes the audio tracks independently in parallel and provides the audio tracks to the speaker system for presentation with the augmented reality objects.

Snap Inc. patent applications on September 5th, 2024