公开(公告)号：US20250166368A1

公开(公告)日：2025-05-22

申请号：US18943855

申请日：2024-11-11

Applicant: Sony Interactive Entertainment Inc.

Inventor： Patrick John Connor ,  Daniel Spong

IPC: G06V10/86 ,  A63F13/60 ,  G06T15/04 ,  G06T19/20

Abstract: A computer-implemented method comprises obtaining a set of initial graphics assets for a video game, an initial graphics asset comprising at least initial model data for an object, obtaining text data from one or more data sources, inputting at least some of the text data to a machine learning model, generating one or more respective images in dependence on the text data using the machine learning model, and modifying the set of initial graphics assets for the video game in dependence upon one or more of the respective images generated using the machine learning model.

公开(公告)号：US20250166327A1

公开(公告)日：2025-05-22

申请号：US18948151

申请日：2024-11-14

Applicant: Sony Interactive Entertainment Inc.

Inventor： Guy Moss

IPC: G06T19/20

Abstract: A content generation system, comprising: receiving circuitry configured to receive environment geometry data of at least part of a three-dimensional, 3D, virtual environment; selecting circuitry comprising a selecting model trained to select, based on the received environment geometry data, one or more virtual elements; and generating circuitry configured to instantiate the selected virtual elements within the at least part of the virtual environment.

公开(公告)号：US20250165789A1

公开(公告)日：2025-05-22

申请号：US19013693

申请日：2025-01-08

Applicant: Sony Interactive Entertainment Inc.

Inventor： Sudha Krishnamurthy

IPC: G06N3/084 ,  G06F16/68 ,  G06N3/045 ,  G06N20/00 ,  G10L15/16

Abstract: A Sound effect recommendation network is trained using a machine learning algorithm with a reference image, a positive audio embedding and a negative audio embedding as inputs to train a visual-to-audio correlation neural network to output a smaller distance between the positive audio embedding and the reference image than the negative audio embedding and the reference image. The visual-to-audio correlation neural network is trained to identify one or more visual elements in the reference image and map the one or more visual elements to one or more sound categories or subcategories within an audio database.

公开(公告)号：US20250157192A1

公开(公告)日：2025-05-15

申请号：US18832913

申请日：2022-12-23

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Daisuke TSURU ,  Masaki UCHIDA ,  Yuto HAYAKAWA ,  Mitsuru NISHIBE

IPC: G06V10/764 ,  G06T7/30 ,  G06T7/73 ,  G06V10/44

Abstract: An image forming device tracks a state of a head mounted display by Visual SLAM on the basis of a captured image of a space around a user wearing the head mounted display. The image forming device determines keyframes collated with a current frame during (a) setting of a play area (step S50), and classifies some of the determined keyframes into keyframes prohibiting discard (step S52). The image forming device reads stored keyframe data and uses the read keyframe data for tracking during (b) execution of an application (step S60). The image forming device adds keyframes and discards pieces of data of keyframes allowing discard according to movement of the user (step S64).

公开(公告)号：US20250157143A1

公开(公告)日：2025-05-15

申请号：US18727110

申请日：2022-12-19

Applicant: Sony Interactive Entertainment Inc.

Inventor： Takeshi NAKAGAWA ,  Takashi HATAKEDA ,  Kuniaki OE ,  Shizuka OHARA ,  Haruka IWAKI

IPC: G06T17/00 ,  G02B27/01 ,  G06F3/01 ,  G06T5/50 ,  G06T7/70

Abstract: An image generation device generates a look-around screen for allowing a user who wears a head-mounted display to look around a play area. The image generation device generates a map for estimating a position of the user, on the basis of a plurality of camera images obtained by capturing a space around the user in a plurality of directions by a camera of the head-mounted display. In the look-around screen, a predetermined special image is superimposed on an image indicating the play area, and a region which has coincided with the line-of-sight direction of the user in a special image changes a display mode different than before. The special image is set to a space around the head-mounted display and narrower than a maximum range of the play area.

公开(公告)号：US12301899B2

公开(公告)日：2025-05-13

申请号：US18420728

申请日：2024-01-23

Applicant: Sony Interactive Entertainment Inc.

Inventor： Claes Christian Rickeby

IPC: H04N21/2343 ,  A63F13/335 ,  A63F13/355 ,  A63F13/358 ,  H04L47/26 ,  H04L67/131 ,  H04N19/146 ,  H04N21/478

Abstract: Methods and system include receiving frames of data generated for an online game, from a server device and encoding the frames using an encoder. Each encoded frame of data is transmitted to a client device over a network, for rendering. A monitoring engine is used to evaluate the data contained in the encoded frame to determine if an amount of data contained in the encoded frame exceeds a maximum data limit specified for a communication channel established between the server device and the client device. When the amount of data contained in the encoded frame exceeds the maximum data limit, a signal is sent to the encoder to dynamically reduce amount of data included in one or more subsequent frames forwarded to the client device for rendering. The adjusting is performed to maintain a frame rate defined for the online game.

公开(公告)号：US20250148568A1

公开(公告)日：2025-05-08

申请号：US18923559

申请日：2024-10-22

Applicant: Sony Interactive Entertainment Inc.

Inventor： Rosario Leonardi ,  Patrick John Connor

IPC: G06T3/4007 ,  G02B27/01

Abstract: There is provided an image processing method. The method includes receiving an image, receiving gaze data indicative of a gaze location of a user for the image, performing an upscaling process on at least part of the received image to increase quality of the at least part of the received image, and outputting the upscaled image to a display device. Performing the upscaling process includes upscaling a first region of the received image corresponding to the gaze location of the user for the image using a first kernel size and upscaling a second region of the received image using a second kernel size, where the first kernel size is larger than the second kernel size.

公开(公告)号：US20250148195A1

公开(公告)日：2025-05-08

申请号：US19019235

申请日：2025-01-13

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Warren Benedetto ,  Charlie Wayne Denison

IPC: G06F40/166 ,  G06F3/0482 ,  G06F3/0484 ,  G06F40/279 ,  G06T11/60

Abstract: Methods and system for generating an image for a user prompt provided by a user includes receiving the user prompt from the user. The user prompt is analyzed to detect text input and keywords included within. Keyword variations are provided to one or more keywords for user selection. An adjusted user prompt is generated by replacing keywords in the user prompt with keyword variations selected by the user. An image customized for the adjusted user prompt is generated to include image features that are influenced by content of the adjusted user prompt. The customized image providing a visual representation of the adjusted prompt is returned to a client device for rendering.

公开(公告)号：US12293752B2

公开(公告)日：2025-05-06

申请号：US18045167

申请日：2022-10-09

Applicant: Sony Interactive Entertainment Inc.

Inventor： Sarah Karp ,  Celeste Bean ,  Tatianna Manzon-Gutzman

IPC: G10K11/178

Abstract: To avoid startling a computer game player immersed in virtual reality for example, active noise cancelation is gradually introduced. As an alternative, ambient noise is gradually increased to conceal loud external sounds. The noise cancelation or ambient noise generation is established according to sound exceeding a background threshold as detected by a microphone. The noise cancelation or ambient noise generation can be established according to images of a noisy object as imaged by a camera.

公开(公告)号：US20250138326A1

公开(公告)日：2025-05-01

申请号：US18835354

申请日：2023-02-20

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Yusuke TAKAHASHI ,  Motohiro NISHIHATA ,  Masashi MURATA

IPC: G02B27/01 ,  G06F3/01 ,  H02K7/06 ,  H02P3/08

Abstract: Rotation of a DC motor (423) for vibration used for a head-mounted display (12) is stabilized.
A drive control system (100) includes a vibration section (42) including at least the DC motor (423) and provided in the HMD 12 including a display panel (38) disposed before eyes of a user when the user wears the HMD 12, and a motor control section (60) outputting a drive signal for controlling drive force that drives the vibration section (42), and the motor control section (60) outputs, in a predetermined startup period (T1), a first drive signal (DP1) causing the vibration section (42) to be driven by first drive force, and, after the startup period (T1) elapses, outputs a second drive signal (DP2) driving the vibration section (42) using second drive force smaller than the first drive force and including a plurality of single pulses to be intermittently output.