公开(公告)号：US20250095283A1

公开(公告)日：2025-03-20

申请号：US18468622

申请日：2023-09-15

Applicant: QUALCOMM Incorporated

Inventor： Eran PINHASOV ,  Eran SCHARAM

IPC: G06T15/50 ,  G06T7/194 ,  G06T7/70 ,  H04N5/272 ,  H04N5/74 ,  H04N23/68

Abstract: Systems and techniques are provided for processing image data. A process can include determining an estimated camera pose corresponding to image data and generating a background replacement view of a configured three-dimensional (3D) content. The background replacement view can be associated with an angle-of-view (AOV) based on the estimated camera pose. A segmentation mask can be determined for the image data, indicative of a foreground portion of the image data and a background portion of the image data. A relighting image can be generated corresponding to at least a portion of the image data, wherein the relighting image is based on the segmentation mask and lighting information of the configured 3D content. An output image can be generated based on the relighting image and the background replacement view of the configured 3D content.

公开(公告)号：US20220060619A1

公开(公告)日：2022-02-24

申请号：US17158917

申请日：2021-01-26

Applicant: QUALCOMM Incorporated

Inventor： Eran PINHASOV ,  Scott CHENG ,  Eran SCHARAM ,  Anatoly GUREVICH

IPC: H04N5/232 ,  G06K9/00

Abstract: Examples are described for applying different settings for image capture to different portions of image data. For example, an image sensor can capture image data of a scene and can send the image data to an image signal processor (ISP) and a classification engine for processing. The classification engine can determine that a first object image region depicts a first category of object, and a second object image region depicts a second category of object. Different confidence regions of the image data can identify different degrees of confidence in the classifications. The ISP can generate an image by applying a different settings to the different portions of the image data. The different portions of the image data can be identified based on the object image regions and confidence regions.

公开(公告)号：US20240121521A1

公开(公告)日：2024-04-11

申请号：US18545799

申请日：2023-12-19

Applicant: QUALCOMM Incorporated

Inventor： Eran PINHASOV ,  Scott CHENG ,  Eran SCHARAM ,  Anatoly GUREVICH

IPC: H04N23/80 ,  G06V10/10 ,  G06V20/00 ,  G06V20/10 ,  H04N1/60 ,  H04N23/61 ,  H04N23/66 ,  H04N23/70

CPC classification number: H04N23/80 ,  G06V10/10 ,  G06V20/10 ,  G06V20/35 ,  H04N1/6072 ,  H04N1/6083 ,  H04N23/61 ,  H04N23/66 ,  H04N23/70 ,  H04N2101/00

Abstract: Examples are described for applying different settings for image capture to different portions of image data. For example, an image sensor can capture image data of a scene and can send the image data to an image signal processor (ISP) and a classification engine for processing. The classification engine can determine that a first object image region depicts a first category of object, and a second object image region depicts a second category of object. Different confidence regions of the image data can identify different degrees of confidence in the classifications. The ISP can generate an image by applying a different settings to the different portions of the image data. The different portions of the image data can be identified based on the object image regions and confidence regions.