公开(公告)号：US20160232672A1

公开(公告)日：2016-08-11

申请号：US14825932

申请日：2015-08-13

Applicant: QUALCOMM Incorporated

Inventor： Ramin Rezaiifar

IPC: G06T7/00 ,  G06T11/60 ,  H04N5/235 ,  G06T7/20 ,  H04N5/225 ,  H04N5/232

CPC classification number: G06T11/60 ,  G06T7/20 ,  G06T7/215 ,  G06T7/254 ,  G06T7/73 ,  G06T2207/20221 ,  H04N5/2256 ,  H04N5/23212 ,  H04N5/2353

Abstract: Systems and methods described herein can compensate for aberrations produced by a moving object in an image captured using a flash. In some embodiments, a method includes capturing a first image at time t−Δt1, where Δt1 represents the time difference between capturing the first image and capturing the second image, capturing the second image at a time t, the second image captured using a flash. The method also includes capturing a third image at a time t+Δt2, where Δt2 represents the time difference between capturing the second image and capturing the third image, determining motion information of an object that is depicted in the first, second and third image, and modifying at least one portion of the second image using the motion information and a portion of the first image, a portion of the third image, or a portion of the first image and a portion of the third image.

Abstract translation: 本文描述的系统和方法可以补偿使用闪光捕获的图像中由移动物体产生的像差。 在一些实施例中，一种方法包括在时间t-Δt1处捕获第一图像，其中Δt1表示捕获第一图像和捕获第二图像之间的时间差，在时间t拍摄第二图像，使用闪光捕获的第二图像 。 该方法还包括在时间t +Δt2处拍摄第三图像，其中Δt2表示拍摄第二图像和拍摄第三图像之间的时间差，确定在第一图像，第二图像和第三图像中描绘的对象的运动信息， 以及使用运动信息和第一图像的一部分，第三图像的一部分，或第一图像的一部分和第三图像的一部分来修改第二图像的至少一部分。

公开(公告)号：US09338349B2

公开(公告)日：2016-05-10

申请号：US14012534

申请日：2013-08-28

Applicant: QUALCOMM Incorporated

Inventor： Piyush Sharma ,  Nitesh Shroff ,  Ramin Rezaiifar ,  Chiachi Sung

IPC: H04N5/232 ,  G06T5/00 ,  G06T5/50 ,  H04N5/235

CPC classification number: H04N5/23229 ,  G06T5/007 ,  G06T5/50 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20212 ,  H04N5/23238 ,  H04N5/2355

Abstract: Apparatuses and methods for reading a set of images to merge together into a high dynamic range (HDR) output image are described. Images have a respective HDR weight and a respective ghost-free weight. Images are merged together using the weighted average of the set of input images using the ghost-free weight. A difference image is determined based on a difference between each pixel within a HDR output image and each respective pixel within a reference image used to create the HDR output image.

Abstract translation: 描述用于读取一组图像以将其合并成高动态范围（HDR）输出图像的装置和方法。 图像具有相应的HDR权重和相应的无重影重量。 使用无重影重量的输入图像集合的加权平均值将图像合并在一起。 基于HDR输出图像内的每个像素与用于创建HDR输出图像的参考图像中的每个相应像素之间的差异来确定差异图像。

公开(公告)号：US20150195464A1

公开(公告)日：2015-07-09

申请号：US14252560

申请日：2014-04-14

Applicant: QUALCOMM Incorporated

Inventor： Piyush Sharma ,  Chao Jia ,  Ramin Rezaiifar

IPC: H04N5/353 ,  H04N5/235

CPC classification number: H04N5/3537 ,  H04N5/23277 ,  H04N5/2355 ,  H04N9/045

Abstract: Methods, devices, and computer program products for capturing images with reduced blurriness in low light conditions are contained herein. In one aspect, a method of capturing an image is disclosed. The method includes capturing a plurality of first images with a first exposure length. The method further includes aligning each of the plurality of first images with each other and combining the aligned plurality of first images into a combined first image. The method further includes capturing a second image with a second exposure length, wherein the second exposure length is longer than the first exposure length and using the second image to adjust the brightness of the combined first image.

Abstract translation: 本文包含用于在低光条件下捕获具有降低的模糊度的图像的方法，装置和计算机程序产品。 一方面，公开了拍摄图像的方法。 该方法包括以第一曝光长度捕获多个第一图像。 该方法还包括将多个第一图像中的每一个彼此对准，并将对准的多个第一图像组合成组合的第一图像。 该方法还包括以第二曝光长度拍摄第二图像，其中第二曝光长度比第一曝光长度长，并且使用第二图像来调整组合的第一图像的亮度。

公开(公告)号：US20150062370A1

公开(公告)日：2015-03-05

申请号：US14471416

申请日：2014-08-28

Applicant: QUALCOMM Incorporated

Inventor： Nitesh Shroff ,  Ramin Rezaiifar ,  Piyush Sharma

IPC: H04N5/232 ,  G06T7/00 ,  H04N5/222

CPC classification number: H04N5/23212 ,  G06T5/003 ,  G06T7/571 ,  G06T2200/21 ,  G06T2207/10028 ,  H04N5/2226

Abstract: Techniques are described for generating an all-in focus image with a capability to refocus. One example includes obtaining a first depth map associated with a plurality of captured images of a scene. The plurality of captured images may include images having different focal lengths. The method further includes obtaining a second depth map associated with the plurality of captured images, generating a composite image showing different portions of the scene in focus (based on the plurality of captured images and the first depth map), and generating a refocused image showing a selected portion of the scene in focus (based on the composite image and the second depth map).

Abstract translation: 描述了用于产生具有重新聚焦能力的全焦点图像的技术。 一个示例包括获得与场景的多个捕获图像相关联的第一深度图。 多个拍摄图像可以包括具有不同焦距的图像。 该方法还包括获得与多个拍摄图像相关联的第二深度图，生成示出对焦的场景的不同部分（基于多个拍摄图像和第一深度图）的合成图像，以及生成重新聚焦图像，其显示 对焦的场景的选定部分（基于合成图像和第二深度图）。

公开(公告)号：US20140375865A1

公开(公告)日：2014-12-25

申请号：US14309551

申请日：2014-06-19

Applicant: QUALCOMM Incorporated

Inventor： Nitesh SHROFF ,  Ramin Rezaiifar ,  Chiachi Sung

IPC: H04N5/232 ,  G06T5/00

CPC classification number: H04N5/23216 ,  G06T3/4053 ,  G06T5/00

Abstract: Systems, devices, and methods are described for efficiently super resolving a portion of an image. One embodiment involves capturing, using a camera module of a device, at least one image of a scene, and creating a higher resolution image of a user-selected region of interest. The super resolution of the region of interest may be performed by matching a high resolution grid with a grid that is at the resolution of a device camera, populating the high resolution grid with information from an image from the camera, and then populating the remaining points of the grid that are not yet populated.

Abstract translation: 描述了用于有效地超分辨图像的一部分的系统，设备和方法。 一个实施例涉及使用设备的相机模块来捕获场景的至少一个图像，以及创建用户选择的感兴趣区域的较高分辨率图像。 感兴趣区域的超分辨率可以通过将高分辨率网格与处于设备相机的分辨率的网格进行匹配来进行，使用来自相机的图像的信息填充高分辨率网格，然后填充剩余点 的网格尚未填充。

公开(公告)号：US20130303222A1

公开(公告)日：2013-11-14

申请号：US13947431

申请日：2013-07-22

Applicant: QUALCOMM Incorporated

Inventor： Peerapol Tinnakornsrisuphap ,  Parag Arun Agashe ,  Ramin Rezaiifar ,  Bibhu P. Mohanty ,  Paul E. Bender

IPC: H04W76/02

CPC classification number: H04W76/02 ,  H04W36/10 ,  H04W36/12 ,  H04W76/10

Abstract: Embodiments described herein relate to connected-state radio session transfer in wireless communications. A target access network controller may create a radio session associated with an access terminal, the radio session corresponding with a source radio session at a source access network controller. The target access network controller may also establish a communication route between a data network and the access terminal via the target access network controller. The target access network controller may further receive a frozen state associated with the source radio session from the source access network controller. In an aspect, the frozen state may include a snapshot of any data being communicated through the source radio session when freezing occurred. The target access network controller may subsequently unfreeze the received state.

Abstract translation: 本文描述的实施例涉及无线通信中的连接状态无线电会话传送。 目标接入网络控制器可以创建与接入终端相关联的无线电会话，无线电会话对应于源接入网络控制器处的源无线电会话。 目标接入网络控制器还可以经由目标接入网络控制器建立数据网络和接入终端之间的通信路由。 目标接入网络控制器还可以从源接入网络控制器接收与源无线电会话相关联的冻结状态。 在一方面，冻结状态可以包括当发生冷冻时通过源无线电会话通信的任何数据的快照。 目标接入网络控制器随后可以解冻所接收的状态。

公开(公告)号：US10992873B2

公开(公告)日：2021-04-27

申请号：US16294907

申请日：2019-03-06

Applicant: QUALCOMM Incorporated

Inventor： Reza Pourreza Shahri ,  Ramin Rezaiifar

IPC: H04N5/235 ,  G06F9/30 ,  G06T7/90 ,  H04N13/254

Abstract: Systems, methods, and computer-readable media are provided for transferring color information from a no-flash image of a scene to a flash image of the scene using a localized tonal mapping algorithm. In some aspects, an example method can include obtaining a no-flash image and a flash image, mapping color information from the no-flash image to the flash image, and generating an output image including the flash image modified based on the mapping to include at least a portion of the color information from the no-flash image.

公开(公告)号：US10977802B2

公开(公告)日：2021-04-13

申请号：US16116763

申请日：2018-08-29

Applicant: QUALCOMM Incorporated

Inventor： Sunid Wilson ,  Ramin Rezaiifar

IPC: G06T7/215 ,  G06T7/194 ,  G06T7/11 ,  G06T7/174

Abstract: Techniques and systems are provided for segmenting one or more frames. For example, incremental optical flow maps can be determined between adjacent frames of a plurality of frames. Using the incremental optical flow maps, a cumulative optical flow map can be determined between a first frame of the plurality of frames and a last frame of the plurality of frames. A segmentation mask can be determined using the first frame of the plurality of frames. Foreground pixels of the segmentation mask for the last frame of the plurality of frames can then be adjusted relative to corresponding foreground pixels for the first frame. The foreground pixels can be adjusted using the cumulative optical flow map between the first frame and the last frame of the plurality of frames.

公开(公告)号：US10818081B2

公开(公告)日：2020-10-27

申请号：US16814787

申请日：2020-03-10

Applicant: QUALCOMM Incorporated

Inventor： Ramin Rezaiifar ,  Antwan Gaggi ,  Donna Roy

IPC: G06T15/50 ,  G06T7/194 ,  G06T7/593 ,  G06T7/586 ,  G06T7/50 ,  G06T15/80 ,  G06F3/0484 ,  G06F3/01 ,  G06F3/16

Abstract: Techniques and systems are described herein for determining dynamic lighting for objects in images. Using such techniques and systems, a lighting condition of one or more captured images can be adjusted. Techniques and systems are also described herein for determining depth values for one or more objects in an image. In some cases, the depth values (and the lighting values) can be determined using only a single camera and a single image, in which case one or more depth sensors are not needed to produce the depth values.

公开(公告)号：US10290111B2

公开(公告)日：2019-05-14

申请号：US15413225

申请日：2017-01-23

Applicant: QUALCOMM Incorporated

Inventor： Chao Jia ,  Ramin Rezaiifar

IPC: G06K9/32 ,  G06T7/33 ,  G06T7/13 ,  G06T3/00 ,  G06T5/50 ,  H04N5/225 ,  H04N5/265 ,  H04N5/232

Abstract: A method for compositing images by an electronic device is described. The method includes obtaining a first composite image that is based on a first image from a first lens with a first focal length and a second image from a second lens with a different second focal length. The method also includes downsampling the first composite image to produce a downsampled first composite image. The method further includes downsampling the first image to produce a downsampled first image. The method additionally includes producing a reduced detail blended image based on the downsampled first composite image and the downsampled first image. The method also includes producing an upsampled image based on the reduced detail blended image and the downsampled first composite image. The method further includes adding detail from the first composite image to the upsampled image to produce a second composite image.