公开(公告)号：WO2022237435A1

公开(公告)日：2022-11-17

申请号：PCT/CN2022/086428

申请日：2022-04-12

Applicant: 北京字节跳动网络技术有限公司

Inventor： 陈映宜 ,  焦少慧

IPC: H04N21/2187 ,  G06T7/194 ,  H04N21/23418 ,  H04N21/234345 ,  H04N21/44012 ,  H04N21/440245

Abstract: 本实施例提供的更换画面中的背景的方法、设备、存储介质及程序产品，涉及图像处理技术，包括：获取预设场景的基础背景图；其中，基础背景图是预先拍摄预设场景得到的图像；获取当前拍摄预设场景所得到的拍摄画面，并根据基础背景图和拍摄画面确定预设场景的当前背景图；使用预设背景图替换拍摄画面中的当前背景图，得到最终拍摄画面。本实施例提供的方案中，能够利用预先采集的基础背景图识别当前拍摄画面中的当前背景图，进而可以利用预设背景图替换拍摄画面中的当前背景图，这种方式无需在预设场景中设置特定的背景装置，就能够根据需求调整拍摄画面中的背景，从而提高更换拍摄画面中的背景的灵活度。

公开(公告)号：WO2022240205A1

公开(公告)日：2022-11-17

申请号：PCT/KR2022/006783

申请日：2022-05-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： YIP, Eric ,  YANG, Hyunkoo ,  SONG, Jaeyeon

IPC: H04N21/84 ,  H04N21/858 ,  H04N21/4725 ,  H04N21/472 ,  H04N21/81 ,  H04L65/00 ,  H04L67/131 ,  H04L67/141 ,  H04N21/44004 ,  H04N21/44012 ,  H04N21/47202 ,  H04N21/4825 ,  H04N21/816 ,  H04N21/8586 ,  H04W4/18

Abstract: The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. According to embodiment, the method includes receiving, from a server, an SD based on URL information obtained from an AR/MR application, processing the SD, configuring at least one media buffer pipeline for a media object of a scene, based on the processed SD, and establishing transport sessions for components of the media object.

公开(公告)号：WO2021202043A1

公开(公告)日：2021-10-07

申请号：PCT/US2021/020637

申请日：2021-03-03

Applicant: SNAP INC.

Inventor： VOSS, Jeremy ,  DYER, Dallin

IPC: G06T13/40 ,  H04N21/414 ,  H04M1/72439 ,  H04N7/14 ,  H04N21/4223 ,  H04N21/43 ,  H04N21/44 ,  H04N21/442 ,  H04N21/45 ,  H04N21/4788 ,  H04N21/81 ,  H04N21/84 ,  G06F21/32 ,  G06K9/00275 ,  G06K9/00315 ,  G06T13/80 ,  H04N21/41407 ,  H04N21/4302 ,  H04N21/44008 ,  H04N21/44012 ,  H04N21/44218 ,  H04N21/4532 ,  H04N21/816 ,  H04N7/157

Abstract: A method for operating a messaging system is provided. The method is adapted to send and receive modifiable videos and includes receiving, by a computing device, a first authorization from a user to use a self-image of the user in a personalized video. The method also includes receiving, by the computing device, a second authorization from the user to enable use of another self-image of another user in the personalized video. The method further includes sending, by the computing device, after the first and second authorizations have been received, the personalized video including at least part of the self-image of the user, at least part of the other self-image of the other user, and at least part of a stock video. A system and a non-transitory processor-readable medium for operating a messaging system adapted to send and receive modifiable videos are provided.

公开(公告)号：WO2022237281A1

公开(公告)日：2022-11-17

申请号：PCT/CN2022/078652

申请日：2022-03-01

Applicant: 广东欧谱曼迪科技有限公司

Inventor： 韩防 ,  梁江荣 ,  任均宇 ,  安昕 ,  张浠

IPC: H04N21/234 ,  H04N21/23412 ,  H04N21/42653 ,  H04N21/44012 ,  H04N21/8547

Abstract: 本发明公开了一种图像标记数据处理还原系统、处理方法、还原方法、装置，通过在图像上叠加灰度图像，在灰度图像上进行信息标记，然后将带有信息标记的灰度图像坍缩成二进制数据，将二进制数据传输至其他数据端，其他数据端接收二进制数据，并将二进制数据还原成带有标记信息的灰度图像，再与原始图像进行叠加，输出带有标记信息的图像，以实现不同数据端的图像标记信息的快速传输；通过将图像标记信息转换成二进制数据进行传输，二进制数据的传输量少，传输速度快，可以解决传统不同数据端之间图像标记信息传输延时的问题；当传输的图像标记信息体量较大时，本技术方案能有效降低数据传输延时，提高不同数据端之间图像标记信息的传输及时性。

公开(公告)号：WO2022032161A1

公开(公告)日：2022-02-10

申请号：PCT/US2021/045051

申请日：2021-08-06

Applicant: VID SCALE, INC.

Inventor： GUDUMASU, Srinivas ,  HAMZA, Ahmed

IPC: H04N21/218 ,  H04N21/44 ,  H04N21/81 ,  H04N21/21805 ,  H04N21/44012 ,  H04N21/8146 ,  H04N21/816

Abstract: A method and apparatus include receiving a timed‑metadata track identifying point cloud tiles corresponding to one or more spatial regions within a point cloud scene. A decoding device determines one or more point cloud tiles to be used for rendering an image. One or more geometry tile tracks are retrieved, via a communications network, corresponding to the determined one or more point cloud tiles. Each geometry tile track comprises point cloud geometry data for a respective tile. The retrieved geometry tile tracks are processed

公开(公告)号：WO2021262660A1

公开(公告)日：2021-12-30

申请号：PCT/US2021/038390

申请日：2021-06-22

Applicant: QUALCOMM INCORPORATED

Inventor： BOUAZIZI, Imed ,  STOCKHAMMER, Thomas

IPC: H04N21/234 ,  H04N21/44 ,  H04N21/472 ,  H04N21/858 ,  G06F9/541 ,  H04L65/60 ,  H04N21/23412 ,  H04N21/44004 ,  H04N21/44012 ,  H04N21/4621 ,  H04N21/47205 ,  H04N21/84 ,  H04N21/8586

Abstract: Techniques are provided for processing media content. For example, a process can include using a scene description to obtain media information and buffer information for a media object. The media information can identify an expected format for storing the media object in one or more output buffers of a media pipeline. The buffer information can include output buffer attributes. The process can include using the media information and the buffer information to initialize the media pipeline for the media object. The process can include obtaining the media object in a delivery format and generating one or more processed media objects. Each processed media object can be converted from the delivery format to the expected format for storing the processed media object in an output buffer. The process can include outputting the processed media object(a) to the output buffer(s) using the initialized media pipeline.

公开(公告)号：WO2022005655A1

公开(公告)日：2022-01-06

申请号：PCT/US2021/034453

申请日：2021-05-27

Applicant: AT&T MOBILITY II LLC

Inventor： PETAJAN, Eric David

IPC: H04N21/234 ,  G11B27/10 ,  H04L29/06 ,  H04N5/272 ,  H04N21/2343 ,  H04N21/414 ,  H04N21/426 ,  H04N21/431 ,  H04N21/44 ,  H04N21/472 ,  H04N21/654 ,  H04N21/81 ,  H04N21/235 ,  H04N21/435 ,  H04N21/6543 ,  H04N21/84 ,  H04N19/20 ,  G06N20/00 ,  G06T13/80 ,  G06T9/00 ,  H04L65/60 ,  H04N19/27 ,  H04N19/44 ,  H04N21/23412 ,  H04N21/23418 ,  H04N21/234318 ,  H04N21/41407 ,  H04N21/42653 ,  H04N21/44012 ,  H04N21/47205 ,  H04N21/8146

Abstract: Aspects of the subject disclosure may include, for example, a method that includes obtaining, by a processing system including a processor, video frames over a network; the processing system uses a machine learning algorithm to identify in each frame a first region comprising a natural image and a second region comprising a synthetic graphic image. The processing system separates the natural image from the synthetic graphic image to generate a natural video and a graphics video, encodes the natural video, and processes the graphics video to generate instructions for rendering graphic images at a client system. The client system performs a decoding procedure for the encoded video, a rendering procedure for client-side graphics in accordance with the instructions, and a compositing procedure to obtain a presentable video stream including the natural image and a client-side graphic corresponding to the synthetic graphic image. Other embodiments are disclosed.

公开(公告)号：WO2022001508A1

公开(公告)日：2022-01-06

申请号：PCT/CN2021/095994

申请日：2021-05-26

Applicant: 腾讯科技（深圳）有限公司

Inventor： 齐国鹏 ,  陈仁健

IPC: H04N21/239 ,  H04N21/44 ,  H04N21/4402 ,  H04N21/478 ,  H04N5/262 ,  H04N21/2393 ,  H04N21/44012 ,  H04N21/4781

Abstract: 本申请提供了一种视频特效的处理方法、装置、电子设备及计算机可读存储介质；方法包括：获取视频特效文件，并从所述视频特效文件中提取时长伸缩策略；获取将所述视频特效文件应用于设计场景时需要实现的目标播放时长，其中，所述目标播放时长区别于所述视频特效文件的原始播放时长；根据所述时长伸缩策略，确定所述视频特效文件中与目标时间轴对应的特效帧；其中，所述目标时间轴的长度与所述目标播放时长一致；根据与所述目标时间轴对应的特效帧进行渲染，得到符合所述目标播放时长的目标视频特效。

公开(公告)号：WO2021252102A1

公开(公告)日：2021-12-16

申请号：PCT/US2021/030787

申请日：2021-05-05

Applicant: TENCENT AMERICA LLC

Inventor： HINDS, Arianne

IPC: H04N21/20 ,  H04N21/60 ,  G06F3/012 ,  G06F3/014 ,  H04L65/4069 ,  H04L65/601 ,  H04L65/602 ,  H04L65/607 ,  H04N21/23412 ,  H04N21/4223 ,  H04N21/44012 ,  H04N21/44218 ,  H04N21/4431 ,  H04N21/8146 ,  H04N21/816

Abstract: A method, computer system, and computer readable medium are provided for displaying video content. An interface to a presentation engine to enable real-time rendering of a plurality of objects is created whereby the plurality of objects are logically organized together through a plurality of scene graphs, and whereby the plurality of scene graphs is organized a media interchange format. Geometry information of the plurality of scene graphs is updated through the interface to a representation engine. The plurality of objects is streamed based on multi-resolution or multi-tesselation of heterogenous visual geometric objects in each of the scene graphs from among the plurality of scene graphs using the media interchange format.