公开(公告)号：WO2014175995A1

公开(公告)日：2014-10-30

申请号：PCT/US2014/032207

申请日：2014-03-28

Applicant: GOOGLE INC

Inventor： KOKARAM, Anil ,  KELLY, Damien ,  CRAWFORD, Andrew Joseph

IPC: G06T3/40 ,  H04N7/01 ,  H04N13/00

CPC classification number: H04N19/577 ,  H04N7/0127 ,  H04N7/014 ,  H04N19/194 ,  H04N19/44 ,  H04N19/52 ,  H04N19/527 ,  H04N19/53 ,  H04N19/553 ,  H04N19/587 ,  H04N19/59 ,  H04N19/597

Abstract: Pull frame interpolation may include identifying a plurality of input video frames, generating a plurality of motion vectors indicating motion from a first frame of the plurality of input video frames to a second frame of the plurality of input video frames, identifying an interpolation point between the first frame and the second frame, generating a plurality of candidate interpolation motion vectors indicating motion from the first frame to the interpolation point and from the second frame to the interpolation point based on the plurality of motion vectors, selecting an interpolation motion vector from the plurality of candidate interpolation motion vectors based on a metric, and generating an interpolated frame at the interpolation point based on the selected interpolation motion vector.

Abstract translation: 拉框插值可以包括识别多个输入视频帧，产生指示从多个输入视频帧的第一帧到多个输入视频帧中的第二帧的运动的多个运动矢量，识别多个输入视频帧中的插值点 第一帧和第二帧，基于多个运动矢量生成指示从第一帧到内插点以及从第二帧到内插点的运动的多个候选插值运动矢量，从多个运动矢量中选择插值运动矢量 基于度量的候选插值运动矢量，并且基于所选择的插值运动矢量在插值点处生成内插帧。

公开(公告)号：WO2014182577A1

公开(公告)日：2014-11-13

申请号：PCT/US2014/036691

申请日：2014-05-02

Applicant: GOOGLE INC.

Inventor： CARPENTER, Thor ,  KOKARAM, Anil

IPC: G06T5/00 ,  G06K9/00

CPC classification number: G06T5/007 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/30201

Abstract: Implementations generally relate to enhancing content appearance. In some implementations, a method includes receiving an image, selecting a reference object in the image. The method also includes determining one or more image parameter adjustments based on the selected reference object, and applying the one or more image parameter adjustments to the entire image.

Abstract translation: 实现通常涉及增强内容外观。 在一些实现中，一种方法包括接收图像，在图像中选择参考对象。 该方法还包括基于所选择的参考对象来确定一个或多个图像参数调整，以及将一个或多个图像参数调整应用于整个图像。

公开(公告)号：WO2014042971A1

公开(公告)日：2014-03-20

申请号：PCT/US2013/058371

申请日：2013-09-06

Applicant: GOOGLE INC.

Inventor： ZHANG, Jiangyang ,  KOKARAM, Anil ,  MUKHERJEE, Debargha ,  CRAWFORD, Andrew Joseph ,  KELLY, Damien

IPC: G11B20/10 ,  G11B27/28 ,  H04N21/43 ,  G06Q10/10

CPC classification number: G11B27/28 ,  G06K9/00765 ,  G06K9/6277 ,  G06K9/6292 ,  G10H1/368 ,  G10L25/06 ,  G10L25/57 ,  G11B27/10

Abstract: Provided are methods for synchronizing multiple video recordings of the same event using audio signals of the recordings. An algorithm is designed to generate candidate time offsets for pairwise matches of video recordings based on audio signals corresponding to the recordings, and combine the candidate time offsets to obtain the most accurate actual time offset between each pair of recordings. Each candidate time offset for each pairwise match of recordings is assigned a confidence measure indicating how likely it is that the particular time offset is correct for the given pair of recordings. The confidence measure assigned to a particular time offset is based on various components and characteristics of the audio signal pair corresponding to the video recordings.

Abstract translation: 提供了使用记录的音频信号同步相同事件的多个视频记录的方法。 一种算法被设计为基于与记录相对应的音频信号来生成视频记录的成对匹配的候选时间偏移，并且组合候选时间偏移以获得每对记录之间最准确的实际时间偏移。 为记录的每个成对匹配的每个候选时间偏移量分配一个置信度量度，指示特定时间偏移对给定的一对记录是否正确的可能性。 分配给特定时间偏移的置信度基于对应于视频记录的音频信号对的各种组件和特性。

公开(公告)号：WO2013155089A1

公开(公告)日：2013-10-17

申请号：PCT/US2013/035807

申请日：2013-04-09

Applicant: GOOGLE INC.

Inventor： KOKARAM, Anil ,  KELLY, Damien ,  CRAWFORD, Andrew Joseph ,  DENMAN, Hugh Pierre

IPC: G06K9/40

CPC classification number: H04N19/65 ,  G06T5/002 ,  G06T5/40 ,  G06T2207/10016 ,  G06T2207/20182 ,  H04N5/145 ,  H04N19/117 ,  H04N19/142 ,  H04N19/179 ,  H04N19/80 ,  H04N19/85 ,  H04N19/86

Abstract: Described herein are techniques related to noise reduction for image sequences or videos. A noise reduction tool includes a motion estimator configured to estimated motion in the video, a noise spectrum estimator configured to estimate noise in the video, a shot detector configured to trigger the noise estimation process, a noise spectrum validator configured to validate the estimated noise spectrum, and a noise reducer to reduce noise in the video using the estimated noise spectrum.

Abstract translation: 这里描述了与图像序列或视频的降噪有关的技术。 降噪工具包括被配置为估计视频中的运动的运动估计器，被配置为估计视频中的噪声的噪声谱估计器，被配置为触发噪声估计处理的镜头检测器，被配置为验证估计噪声谱 ，以及使用估计的噪声谱减少视频中的噪声的降噪器。

公开(公告)号：WO2018080688A1

公开(公告)日：2018-05-03

申请号：PCT/US2017/053318

申请日：2017-09-25

Applicant: GOOGLE INC.

Inventor： CHEN, Chao ,  LIN, Yao-Chung ,  KOKARAM, Anil ,  BENTING, Steve

IPC: H04N21/2343 ,  H04N21/258

Abstract: Implementations disclose bitrate optimization for multi-representation encoding using playback statistics. A method includes generating multiple versions of a segment of a source video, the versions comprising encodings of the segment at different encoding bitrates for each resolution of the segment, measuring a quality metric for each version of the segment, generating rate-quality models for each resolution of the segment based on the measured quality metrics corresponding to the resolutions, generating a probability model to predict requesting probabilities that representations of the segment are requested, the probability model based on a joint probability distribution of network speed and viewport size that is generated from client-side feedback statistics associated with prior playbacks of other videos, determining an encoding bitrate for each of the representations of the segment based on the rate-quality models and the probability model, and assigning determined encoding bitrates to corresponding representations of the segment.

Abstract translation:

实现公开了使用回放统计的多表示编码的比特率优化。 一种方法包括生成源视频的片段的多个版本，所述版本包括针对片段的每个分辨率的不同编码比特率的片段的编码，测量片段的每个版本的质量度量，生成用于每个片段的速率质量模型 基于对应于分辨率的测量的质量度量来生成分段的分辨率，生成概率模型以预测请求表示分段的表示的请求概率，概率模型基于网络速度和视口大小的联合概率分布， 与其他视频的先前回放相关联的客户端反馈统计;基于速率 - 质量模型和概率模型确定分段的每个表示的编码比特率;以及将确定的编码比特率分配给分段的对应表示。 / p>

公开(公告)号：WO2015077507A1

公开(公告)日：2015-05-28

申请号：PCT/US2014/066713

申请日：2014-11-20

Applicant: GOOGLE INC.

Inventor： BIRKBECK, Neil ,  INGUVA, Isasi ,  KELLY, Damien ,  CRAWFORD, Andrew ,  DENMAN, Hugh ,  TOBIN, Perry ,  BENTING, Steve ,  KOKARAM, Anil ,  DOIG, Jeremy

IPC: H04N21/45 ,  H04N21/236 ,  H04N13/00

CPC classification number: G06F3/0484 ,  G11B27/10 ,  G11B27/34 ,  H04N21/2387 ,  H04N21/242 ,  H04N21/45 ,  H04N21/8455 ,  H04N21/8456 ,  H04N21/8549

Abstract: An interactive multi-view module identifies a plurality of media items associated with a real-world event, each of the plurality of media items comprising a video portion and an audio portion. The interactive multi-view module synchronizes the audio portions of each of the plurality of media items according to a common reference timeline, determines a relative geographic position associated with each of the plurality of media items and presents the plurality of media items in an interactive multi-view player interface based at least on the synchronized audio portions and the relative geographic positions.

Abstract translation: 交互式多视图模块识别与真实世界事件相关联的多个媒体项目，所述多个媒体项目中的每一个包括视频部分和音频部分。 所述交互式多视点模块根据公共参考时间线来同步所述多个媒体项目中的每一个的音频部分，确定与所述多个媒体项目中的每一个相关联的相对地理位置，并将所述多个媒体项呈现在交互式多媒体 至少基于同步的音频部分和相对的地理位置来观看播放器界面。