公开(公告)号：US12293521B2

公开(公告)日：2025-05-06

申请号：US17901429

申请日：2022-09-01

Applicant: QUALCOMM Incorporated

Inventor： Chung-Chi Tsai ,  Shubhankar Mangesh Borse ,  Meng-Lin Wu ,  Venkata Ravi Kiran Dayana ,  Fatih Murat Porikli ,  An Chen

IPC: G06T7/11 ,  G06T7/73 ,  G06V30/19

Abstract: Methods, systems, and apparatuses for image segmentation are provided. For example, a computing device may obtain an image, and may apply a process to the image to generate input image feature data and input image segmentation data. Further, the computing device may obtain reference image feature data and reference image classification data for a plurality of reference images. The computing device may generate reference image segmentation data based on the reference image feature data, the reference image classification data, and the input image feature data. The computing device may further blend the input image segmentation data and the reference image segmentation data to generate blended image segmentation data. The computing device may store the blended image segmentation data within a data repository. In some examples, the computing device provides the blended image segmentation data for display.

公开(公告)号：US12125144B2

公开(公告)日：2024-10-22

申请号：US18480304

申请日：2023-10-03

Applicant: QUALCOMM Incorporated

Inventor： Meng-Lin Wu ,  Chung-Chi Tsai ,  An Chen

IPC: G06T17/20 ,  G06T3/20 ,  G06T3/40 ,  G06T3/60 ,  G06T7/11 ,  G06T7/50 ,  G06T19/20

CPC classification number: G06T17/205 ,  G06T3/20 ,  G06T3/40 ,  G06T3/60 ,  G06T7/11 ,  G06T7/50 ,  G06T19/20 ,  G06T2219/2016

Abstract: Systems and techniques are described herein for modifying the scale and/or position of objects in images. For instance, a system can obtain a two-dimensional (2D) input image from a camera and a three-dimensional (3D) representation of the 2D input image. The system can further determine a first portion of the 3D representation of the 2D input image corresponding to a target object in the 2D input image. The system can adjust a pose of the first portion of the 3D representation of the 2D input image corresponding to the target object. The system can further generate a 2D output image having a modified version of the target object based on the adjusted pose of the first portion of the 3D representation of the 2D input image corresponding to the target object to be output on a display.

公开(公告)号：US20250030954A1

公开(公告)日：2025-01-23

申请号：US18353650

申请日：2023-07-17

Applicant: QUALCOMM Incorporated

Inventor： Kai He ,  Hau Hwang ,  Meng-Lin Wu

IPC: H04N25/46 ,  H04N19/167

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support spatially-adaptive binning and remosaicing of image data. In a first aspect, a method of image processing includes receiving image data comprising at least a portion of an image frame. A first portion of the image data is coded according to a first binning pattern, and a second portion of the image data is coded according to a second binning pattern different from the first binning pattern. Other aspects and features are also claimed and described.

公开(公告)号：US11810256B2

公开(公告)日：2023-11-07

申请号：US17524681

申请日：2021-11-11

Applicant: QUALCOMM Incorporated

Inventor： Meng-Lin Wu ,  Chung-Chi Tsai ,  An Chen

IPC: G06T17/20 ,  G06T7/50 ,  G06T7/11 ,  G06T3/20 ,  G06T3/40 ,  G06T3/60 ,  G06T19/20

CPC classification number: G06T17/205 ,  G06T3/20 ,  G06T3/40 ,  G06T3/60 ,  G06T7/11 ,  G06T7/50 ,  G06T19/20 ,  G06T2219/2016

Abstract: Systems and techniques are described herein for modifying the scale and/or position of objects in images. For instance, a system can obtain a two-dimensional (2D) input image from a camera and a three-dimensional (3D) representation of the 2D input image. The system can further determine a first portion of the 3D representation of the 2D input image corresponding to a target object in the 2D input image. The system can adjust a pose of the first portion of the 3D representation of the 2D input image corresponding to the target object. The system can further generate a 2D output image having a modified version of the target object based on the adjusted pose of the first portion of the 3D representation of the 2D input image corresponding to the target object to be output on a display.

公开(公告)号：US20250080858A1

公开(公告)日：2025-03-06

申请号：US18462199

申请日：2023-09-06

Applicant: QUALCOMM Incorporated

Inventor： Meng-Lin Wu ,  Venkata Ravi Kiran Dayana ,  Sandesh Ghimire ,  Kai Liu ,  Ching-Fu Chen

IPC: H04N23/741 ,  H04N23/743

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support high dynamic range (HDR) image processing on image frames with temporally-aligned centers to reduce artifacts resulting from fusing image frames with different temporal centers. In some aspects, a method of image processing includes capturing three or more image frames having at least two different exposure lengths. The three or more image frames are processed to obtain two image frames with temporally-aligned centers, and those two image frames are processed in HDR fusion logic to obtain an output HDR image frame. Other aspects and features are also claimed and described.

公开(公告)号：US20250078227A1

公开(公告)日：2025-03-06

申请号：US18462218

申请日：2023-09-06

Applicant: QUALCOMM Incorporated

Inventor： Meng-Lin Wu ,  Venkata Ravi Kiran Dayana ,  Sandesh Ghimire ,  Kai Liu ,  Ching-Fu Chen

IPC: G06T5/00 ,  G06T5/50

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support image signal processing of exposure bracketed image frames. In a first aspect, a method of image processing includes receiving, by at least one processor, image data comprising first image data of a first exposure duration, second image data of a second exposure duration, and third image data of a third exposure duration, wherein the first exposure duration is equal to the third exposure duration; determining, by the at least one processor, fourth image data by subtracting corresponding pixel intensity values of the third image data from the second image data; and determining, by the at least one processor, a first output image frame by combining the fourth image data with the first image data. Other aspects and features are also claimed and described.

公开(公告)号：US11863729B2

公开(公告)日：2024-01-02

申请号：US17481155

申请日：2021-09-21

Applicant: QUALCOMM Incorporated

Inventor： Meng-Lin Wu ,  Venkata Ravi Kiran Dayana

IPC: H04N13/111 ,  G06T7/593 ,  H04N13/128 ,  H04N13/156 ,  H04N13/243 ,  G06V20/00 ,  G06T3/40 ,  H04N13/00

CPC classification number: H04N13/111 ,  G06T3/40 ,  G06T7/593 ,  G06V20/00 ,  H04N13/128 ,  H04N13/156 ,  H04N13/243 ,  G06T2207/10012 ,  G06T2207/20081 ,  H04N2013/0081

Abstract: Systems and techniques are described for processing image data to generate an image with a synthetic depth of field (DoF). An imaging system receives first image data of a scene captured by a first image sensor. The imaging system receives second image data of the scene captured by a second image sensor. The first image sensor is offset from the second image sensor by an offset distance. The imaging system generates, using at least the first image data and the second image data as inputs to one or more trained machine learning systems, an image having a synthetic depth of field corresponding to a simulated aperture size. The simulated aperture size is associated with the offset distance. The imaging system outputs the image.