WO2019141084A1 - 基于虚拟画像的视频通话的方法与设备 - Google Patents

基于虚拟画像的视频通话的方法与设备 Download PDF

Info

Publication number
WO2019141084A1
WO2019141084A1 PCT/CN2018/125601 CN2018125601W WO2019141084A1 WO 2019141084 A1 WO2019141084 A1 WO 2019141084A1 CN 2018125601 W CN2018125601 W CN 2018125601W WO 2019141084 A1 WO2019141084 A1 WO 2019141084A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
portrait
information
virtual
virtual portrait
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/125601
Other languages
English (en)
French (fr)
Chinese (zh)
Inventor
马小捷
胡晨鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Zhangmen Science and Technology Co Ltd
Original Assignee
Shanghai Zhangmen Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Zhangmen Science and Technology Co Ltd filed Critical Shanghai Zhangmen Science and Technology Co Ltd
Priority to JP2020560531A priority Critical patent/JP2021512562A/ja
Publication of WO2019141084A1 publication Critical patent/WO2019141084A1/zh
Priority to US16/931,419 priority patent/US11196962B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/14—Systems for two-way working
    • H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/14—Systems for two-way working
    • H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
    • H04N7/147—Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—Two-dimensional [2D] image generation
    • G06T11/60—Creating or editing images; Combining images with text
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T13/00—Animation
    • G06T13/20—Three-dimensional [3D] animation
    • G06T13/40—Three-dimensional [3D] animation of characters, e.g. humans, animals or virtual beings
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • G06V40/176—Dynamic expression
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a technology for video calling based on virtual portraits.
  • Video calls can help face-to-face real-time interactions with people thousands of miles away.
  • people replace their own avatars in the video with static images, or add video pendants to their own video avatars. This method is not conducive to the protection of user privacy, and less interesting for communication.
  • the purpose of the present application is to provide a method and apparatus for video call based on virtual portraits.
  • a video call method based on a virtual portrait at a first user equipment side wherein the method includes:
  • first video information where the first video information includes a video portrait of the first user
  • replacing the video portrait in the first video information with a virtual portrait comprises:
  • the video portrait in the first video information is replaced with a virtual portrait.
  • the triggering condition comprises at least one of the following:
  • the equipment condition reaches the preset value
  • the workload of replacing the video portrait is below a threshold.
  • the method further includes:
  • the method further includes:
  • determining the virtual portrait comprises:
  • the virtual portrait is determined based on the user's selection operation.
  • determining the virtual portrait comprises:
  • the virtual portrait is determined based on the emotion information.
  • replacing the video portrait in the first video information with a virtual portrait comprises:
  • the video portrait in the video frame is replaced with the virtual portrait.
  • replacing the video portrait in the first video information with a virtual portrait comprises:
  • the video portrait in the video frame is replaced with a virtual portrait that matches the real-time motion information.
  • the method further includes:
  • the virtual portrait that replaces the video portrait in the video frame with the real-time motion information includes:
  • a virtual portrait of the video portrait in the subsequent frame is generated based on the difference information and the virtual portrait replaced by the previous frame.
  • a video call method based on a virtual portrait at a network device side is further provided, wherein the method includes:
  • the first video information includes a video portrait of the first user corresponding to the first user equipment
  • the method further includes:
  • the method further includes:
  • determining the virtual portrait comprises:
  • the virtual portrait is determined based on the user's selection operation.
  • determining the virtual portrait comprises:
  • the virtual portrait is determined based on the emotion information.
  • replacing the video portrait in the first video information with a virtual portrait comprises:
  • the video portrait in the video frame is replaced with the virtual portrait.
  • the replacing the video portrait in the first video information with a virtual portrait includes:
  • the video portrait in the video frame is replaced with a virtual portrait that matches the real-time motion information.
  • the method further includes:
  • the virtual portrait that replaces the video portrait in the video frame with the real-time motion information includes:
  • a virtual portrait of the video portrait in the subsequent frame is generated based on the difference information and the virtual portrait replaced by the previous frame.
  • the present application determines the second video information including the virtual portrait by acquiring the first video information and replacing the video portrait in the first video information with the virtual image. In this way, the virtual image is obtained. Used in video calls, it can increase communication fun and improve communication, thus improving and enriching the user experience.
  • the present application it is also possible to detect emotion information in the video portrait and determine the virtual portrait based on the emotion information. In this way, it is possible to determine a virtual portrait that matches the user's emotions, so that the user can better express the user's emotions in the video call, and feel the emotional state of both parties, thereby narrowing each other's emotions. Distance, communication will be better.
  • the virtual portrait of the video call partner may also be selected, so that after obtaining the video information of the video call partner, the network device replaces the video portrait of the other party with the virtual portrait desired by the local user, thereby The user experience can be better if the local user can see the virtual portrait that he likes.
  • FIG. 1 shows a flow chart of a video call method based on a virtual portrait at a first user equipment side, according to an aspect of the present application
  • FIG. 2 shows a flow chart of a video call method based on a virtual portrait at a network device side according to another aspect of the present application.
  • the terminal, the device of the service network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage,
  • computer readable media does not include non-transitory computer readable media, such as modulated data signals and carrier waves.
  • FIG. 1 illustrates a video call method for virtual portrait based on a first user equipment side, according to an aspect of the present application, wherein the method includes:
  • S11 acquiring first video information, where the first video information includes a video portrait of the first user;
  • the second video information is sent to the network device, so that the network device sends the second video information to the second user equipment corresponding to the second user, to implement the first user equipment and the first Two user equipment video calls.
  • the user equipment includes a device capable of implementing a video call and capable of interacting with the network device.
  • the user equipment includes, but is not limited to, any mobile electronic product that can interact with the user through the touchpad, for example,
  • the mobile electronic products can adopt any operating system, such as an android operating system, an iOS operating system, and the like.
  • the network device includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a plurality of servers; wherein the cloud is composed of a large number of computers or network servers based on Cloud Computing.
  • cloud computing is a kind of distributed computing, a virtual supercomputer composed of a group of loosely coupled computers.
  • the first user equipment acquires the first video information, where the first video information includes a video portrait.
  • the first video information is video information of the first user acquired by the first user equipment by the photographing device, for example, video information acquired by the first user during the video call, wherein the video portrait includes a video.
  • the portrait in the message may include the person's head or the entire portion of the person who can be photographed.
  • the video portrait in the first video information is replaced with a virtual portrait to generate second video information including the virtual portrait.
  • the virtual portrait includes some other portraits of the video portrait, such as some virtual characters or avatars of virtual characters, such as Superman, Iron Man, and the like.
  • the replacing the video portrait in the first video information with a virtual portrait comprises:
  • S123 replaces the video portrait in the video frame with the virtual portrait.
  • the first user equipment acquires a video frame of the first video information, where the first user equipment acquires the first video information, and further Obtaining each video frame or part of the video frame of the first video information.
  • the first user equipment detects a video portrait in the acquired video frame, where the detection of the video portrait can be implemented by image recognition.
  • the video portrait in the video frame is replaced with the virtual portrait, for example, the virtual portrait can be overlaid onto the video portrait of the video frame to implement replacement, etc. .
  • the video portrait of each frame is replaced with a virtual portrait, where the alternative manner may be the virtual
  • the image entirely covers the video portrait, or covers a head region of the video portrait, preferably, when the virtual portrait is a head portrait, covering a head region of the video portrait; when the virtual portrait is a whole body In the case of an image, the video portrait may be entirely covered.
  • the method of replacing the video portrait with the virtual portrait is merely an example, and other existing or future possible ways of replacing the video portrait with the virtual portrait may be applied to This application is also intended to be included within the scope of the present disclosure, which is hereby incorporated by reference.
  • the step S122 further includes: detecting real-time action information in the video portrait; wherein the step S123 comprises: replacing the video portrait in the video frame based on the real-time action information For the virtual portrait.
  • the video portrait in the video frame is detected, further, real-time action information in the video portrait may be detected, for example, the real-time action information includes a mouth motion and a body motion. And so on, further, in the step S123, the video portrait in the video frame is replaced with the virtual portrait based on the motion information.
  • the real-time motion information includes a mouth motion
  • the video portrait may be replaced with the virtual portrait according to the closing of the mouth, for example, the virtual portrait may be closed at a preset frequency.
  • the real-time action information includes a body motion
  • the corresponding body motion may also be performed at a preset frequency, such as waving a hand or the like.
  • the mouth motion or body motion of the virtual portrait is consistent with the motion of the video portrait.
  • the virtual portrait is also opened, that is, the video portrait is performed in each frame.
  • the corresponding body part in the virtual portrait is to be consistent with the video portrait, for example, the closure of the mouth coincides with the closing of the video portrait mouth.
  • the step S123 includes: detecting difference information between a subsequent frame and the previous frame in the video frame; determining the follow-up based on the difference information and the virtual image replaced by the previous frame a virtual portrait of the video portrait in the frame; replacing the video portrait in the subsequent frame with the virtual portrait.
  • the difference information is used to indicate the difference between the respective frames, and therefore, the replacement operation can be simplified according to the difference information between the subsequent video frame and the previous video frame, for example, when the previous one is detected.
  • the mouth of the video portrait in the frame has just begun to open, and the subsequent frames are also the action of opening the mouth, so the video portrait can be replaced by the difference information of the opening of the subsequent frame and the mouth of the previous frame.
  • the mouth of the subsequent frame is sequentially adjusted according to the difference information, for example, the mouth is opened at a certain amplitude.
  • the replacing the video portrait in the first video information with a virtual portrait comprises: replacing the video portrait in the first video information with a virtual portrait when a trigger condition is met.
  • the first user equipment replaces the video portrait in the first video information with a virtual portrait when the trigger condition is met.
  • the triggering condition comprises at least one of the following: 1) acquiring instruction information to the local replacement; 2) the device condition reaches a preset value; and 3) replacing the video portrait with a workload lower than a threshold.
  • the operation of whether to perform the replacement locally may be set on the user equipment side, and the operation of inputting the instruction information may be performed by the user, and when the first user equipment acquires the instruction information of the local replacement, the video is used.
  • the operation of replacing the portrait with a virtual portrait is performed on the first user device side.
  • the replacement operation is also performed on the first user equipment end, where the device condition includes the remaining power of the user equipment itself or the memory condition, etc., to integrate
  • the device condition is determined, and when the device condition reaches a preset value, the first user device performs a replacement operation locally.
  • the replacement operation is also performed at the first user equipment end, where the workload includes replacing the overhead size of the video portrait, for example , the time spent replacing, etc., or the workload can be measured by the size of the video, and the first user equipment will replace when the workload is below the threshold.
  • the method further comprises: S14 (not shown) said first user equipment transmitting a replacement request to said network device to cause said network device to transmit said second user equipment based on said replacement request
  • the video portrait in the video information is replaced with a virtual portrait; and the video information of the second user equipment after the replacement by the network device is received.
  • the user at the first user equipment side can also implement the replacement of the video portrait of the peer user.
  • the local user can send a replacement request to the network device by using the first user equipment, so that The network device replaces the video portrait in the video information sent by the second user equipment with a virtual portrait based on the replacement request.
  • the video of the opposite video call user may be used.
  • the portrait is replaced by "Iron Man”.
  • the local user can set the virtual portrait of the opposite user during the video call, so that the local user can see the virtual portrait he likes, and the user experience will be better. .
  • the method before the replacing the video portrait in the first video information with a virtual portrait, the method further comprises: S15 (not shown) determining the virtual portrait.
  • step S15 comprises: determining the virtual portrait based on a selection operation of the user.
  • the user can select the favorite virtual portrait by himself, thereby causing the user device to determine the virtual portrait based on the user's selection, thereby achieving replacement.
  • the step S15 includes: detecting emotion information in the video portrait; and determining the virtual portrait based on the emotion information.
  • the virtual portrait matching the emotion information may be determined by detecting the emotion information of the user, for example, when detecting that the user in the video is in a happy state, recommending a plurality of virtual portraits with a happy expression for the user. Then, the user selects to finalize a virtual portrait, or directly determines a virtual portrait with a happy expression for the user.
  • the manner of detecting the user's emotional information may be obtained by acquiring the expression information or the sound information of the user in the video, for example, if the user's expression of laughing is detected, the user is in a happy state or the like.
  • the manner of detecting the emotional information of the user is only an example, and other existing or future possible methods for detecting the emotional information, as applicable to the present application, are also included in the protection scope of the present application. Is included here by reference.
  • FIG. 2 illustrates a virtual portrait-based video call method at a network device side according to another aspect of the present application, wherein the method includes:
  • the S21 obtains the first video information that is sent by the first user equipment, where the first video information includes a video portrait of the first user corresponding to the first user equipment;
  • the second video information is sent to the second user equipment, to implement a video call between the first user equipment and the second user equipment.
  • the network device acquires the first video information sent by the first user equipment, where, after the first user equipment establishes a video call with the second user equipment, the first user The device sends the obtained first video information of the user to the network device.
  • the video portrait in the first video information is replaced with a virtual portrait, where the virtual portrait is The determination may be determined by the user selection, or the network device may also determine based on the emotional information of the video portrait.
  • the replacing the video portrait in the first video information with a virtual portrait comprises: S221 (not shown) acquiring a video frame of the first video information; S222 (not shown) detecting Real-time motion information of the video portrait in the video frame; S223 (not shown) replaces the video portrait in the video frame with a virtual portrait matching the real-time motion information.
  • the real-time action information includes, but is not limited to, a mouth motion, a body motion, and the like, wherein the mouth motion or the body motion of the virtual portrait is consistent with the motion of the video portrait, for example, when When the video portrait is opened, the virtual portrait is also opened, that is, when the video portrait replacement is performed every frame, the corresponding body part in the virtual portrait is to be consistent with the video portrait, for example, the closing of the mouth and the video portrait. The mouth is closed.
  • the method further includes: detecting difference information of the real-time action information in the subsequent frame in the video frame and the previous frame, and then based on the difference information and the virtual image replaced by the previous frame, A virtual portrait of the video portrait in the subsequent frame is generated.
  • the replacement operation can be simplified by the difference information, for example, when it is detected that the mouth of the video portrait in the previous frame has just started to open, and the subsequent frames are also the action of opening the mouth, so
  • the difference information between the subsequent frame and the opening of the mouth of the previous frame is replaced by the virtual portrait, wherein when the virtual portrait is replaced, the mouth of the subsequent frame is sequentially performed according to the difference information.
  • Corresponding adjustments for example, the mouth is opened at a certain amplitude.
  • the network device sends the second video information to the second user equipment to implement a video call between the first user equipment and the second user equipment. That is, the network device sends the replaced video information to the second user equipment to implement a video call based on the virtual portrait of the first user equipment and the second user equipment.
  • the present application determines the second video information including the virtual portrait by acquiring the first video information and replacing the video portrait in the first video information with the virtual image. In this way, the virtual image is obtained. Used in video calls, it can increase communication fun and improve communication, thus improving and enriching the user experience.
  • the present application it is also possible to detect emotion information in the video portrait and determine the virtual portrait based on the emotion information. In this way, it is possible to determine a virtual portrait that matches the user's emotions, so that the user can better express the user's emotions in the video call, and feel the emotional state of both parties, thereby narrowing each other's emotions. Distance, communication will be better.
  • the virtual portrait of the video call partner may also be selected, so that after obtaining the video information of the video call partner, the network device replaces the video portrait of the other party with the virtual portrait desired by the local user, thereby The user experience can be better if the local user can see the virtual portrait that he likes.
  • an embodiment of the present application further provides a computer readable medium having stored thereon computer readable instructions executable by a processor to implement the foregoing method.
  • the embodiment of the present application further provides a first user equipment of a video call based on a virtual portrait, where the first user equipment includes:
  • One or more processors are One or more processors;
  • a memory storing computer readable instructions that, when executed, cause the processor to perform the operations of the aforementioned methods.
  • the computer readable instructions when executed, cause the one or more processors to: acquire first video information, wherein the first video information includes a video portrait of a first user; The video portrait is replaced with a virtual portrait to generate second video information including the virtual portrait; the second video information is transmitted to a network device.
  • the embodiment of the present application further provides a network device for video call based on a virtual portrait, where the network device includes:
  • One or more processors are One or more processors;
  • a memory storing computer readable instructions that, when executed, cause the processor to perform the operations of the aforementioned methods.
  • the computer readable instructions when executed, cause the one or more processors to: acquire first video information transmitted by the first user equipment, wherein the first video information includes a first corresponding to the first user equipment a video portrait of a user; replacing the video portrait in the first video information with a virtual portrait to generate second video information including the virtual portrait; and transmitting the second video information to a second user device a video call between the first user equipment and the second user equipment.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Telephone Function (AREA)
PCT/CN2018/125601 2018-01-18 2018-12-29 基于虚拟画像的视频通话的方法与设备 Ceased WO2019141084A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2020560531A JP2021512562A (ja) 2018-01-18 2018-12-29 仮想画像に基づくビデオ通話の方法および装置
US16/931,419 US11196962B2 (en) 2018-01-18 2020-07-16 Method and a device for a video call based on a virtual image

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810050161.XA CN108377356B (zh) 2018-01-18 2018-01-18 基于虚拟画像的视频通话的方法、设备和计算机可读介质
CN201810050161.X 2018-01-18

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/931,419 Continuation US11196962B2 (en) 2018-01-18 2020-07-16 Method and a device for a video call based on a virtual image

Publications (1)

Publication Number Publication Date
WO2019141084A1 true WO2019141084A1 (zh) 2019-07-25

Family

ID=63015860

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/125601 Ceased WO2019141084A1 (zh) 2018-01-18 2018-12-29 基于虚拟画像的视频通话的方法与设备

Country Status (4)

Country Link
US (1) US11196962B2 (https=)
JP (1) JP2021512562A (https=)
CN (1) CN108377356B (https=)
WO (1) WO2019141084A1 (https=)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108377356B (zh) * 2018-01-18 2020-07-28 上海掌门科技有限公司 基于虚拟画像的视频通话的方法、设备和计算机可读介质
CN111614930B (zh) * 2019-02-22 2022-11-25 浙江宇视科技有限公司 一种视频监控方法、系统、设备及计算机可读存储介质
CN113395597A (zh) 2020-10-26 2021-09-14 腾讯科技（深圳）有限公司 一种视频通讯处理方法、设备及可读存储介质
CN112565913B (zh) * 2020-11-30 2023-06-20 维沃移动通信有限公司 视频通话方法、装置和电子设备
CN112925462B (zh) * 2021-04-01 2022-08-09 腾讯科技（深圳）有限公司 账号头像更新方法及相关设备
CN114038034B (zh) * 2021-11-05 2026-02-06 广州市人心网络科技有限公司 虚拟人脸选择模型训练方法、在线视频心理咨询隐私保护方法、存储介质及心理咨询系统
CN114419694A (zh) * 2021-12-21 2022-04-29 珠海视熙科技有限公司 一种多人视频会议头像的处理方法及处理装置
CN116112761B (zh) * 2023-04-12 2023-06-27 海马云（天津）信息技术有限公司 生成虚拟形象视频的方法及装置、电子设备和存储介质
CN117478818B (zh) * 2023-12-26 2024-08-23 荣耀终端有限公司 语音通话方法、终端和存储介质
WO2025145283A1 (en) * 2024-01-02 2025-07-10 Zte Corporation Audio/video transition for wireless communication

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103368929A (zh) * 2012-04-11 2013-10-23 腾讯科技（深圳）有限公司 一种视频聊天方法及系统
CN103647922A (zh) * 2013-12-20 2014-03-19 百度在线网络技术（北京）有限公司 虚拟视频通话方法和终端
CN103916621A (zh) * 2013-01-06 2014-07-09 腾讯科技（深圳）有限公司 视频通信方法及装置
US20140267342A1 (en) * 2013-03-13 2014-09-18 Victor Liu Method of creating realistic and comic avatars from photographs
US20150365627A1 (en) * 2014-06-13 2015-12-17 Arcsoft Inc. Enhancing video chatting
CN106331572A (zh) * 2016-08-26 2017-01-11 乐视控股（北京）有限公司 一种基于图像的控制方法和装置
CN108377356A (zh) * 2018-01-18 2018-08-07 上海掌门科技有限公司 基于虚拟画像的视频通话的方法与设备

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4291963B2 (ja) * 2000-04-13 2009-07-08 富士フイルム株式会社 画像処理方法
JP3593067B2 (ja) * 2001-07-04 2004-11-24 沖電気工業株式会社 画像コミュニケーション機能付き情報端末装置および画像配信システム
JP2003248841A (ja) * 2001-12-20 2003-09-05 Matsushita Electric Ind Co Ltd バーチャルテレビ通話装置
JP2004040525A (ja) * 2002-07-04 2004-02-05 Sony Corp 映像信号の送出装置および送出方法
JP2004064102A (ja) * 2002-07-24 2004-02-26 Matsushita Electric Ind Co Ltd 仮想テレビ電話装置および仮想テレビ電話装置における画像生成方法
JP2005277989A (ja) * 2004-03-26 2005-10-06 Oki Electric Ind Co Ltd 通信端末装置およびその画像提供方法
JP2006235771A (ja) * 2005-02-23 2006-09-07 Victor Co Of Japan Ltd 遠隔操作装置
JP2006287297A (ja) * 2005-03-31 2006-10-19 Yamaha Corp 携帯通信端末、通信端末、中継装置およびプログラム
JP2007174281A (ja) * 2005-12-22 2007-07-05 Kyocera Corp テレビ電話システム、通信端末、中継装置
CN101677386A (zh) * 2008-08-01 2010-03-24 中兴通讯股份有限公司 可选择实时虚拟通话背景的系统及视频通话方法
CN101931621A (zh) * 2010-06-07 2010-12-29 上海那里网络科技有限公司 一种借助虚拟形象进行情感交流的装置和方法
CN102455898A (zh) * 2010-10-29 2012-05-16 张明 视频聊天卡通表情辅助娱乐系统
CN105407313A (zh) * 2015-10-28 2016-03-16 掌赢信息科技（上海）有限公司 一种视频通话方法、设备和系统
JP2017188833A (ja) * 2016-04-08 2017-10-12 ソニー株式会社 情報処理装置および情報処理方法、並びにプログラム

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103368929A (zh) * 2012-04-11 2013-10-23 腾讯科技（深圳）有限公司 一种视频聊天方法及系统
CN103916621A (zh) * 2013-01-06 2014-07-09 腾讯科技（深圳）有限公司 视频通信方法及装置
US20140267342A1 (en) * 2013-03-13 2014-09-18 Victor Liu Method of creating realistic and comic avatars from photographs
CN103647922A (zh) * 2013-12-20 2014-03-19 百度在线网络技术（北京）有限公司 虚拟视频通话方法和终端
US20150365627A1 (en) * 2014-06-13 2015-12-17 Arcsoft Inc. Enhancing video chatting
CN106331572A (zh) * 2016-08-26 2017-01-11 乐视控股（北京）有限公司 一种基于图像的控制方法和装置
CN108377356A (zh) * 2018-01-18 2018-08-07 上海掌门科技有限公司 基于虚拟画像的视频通话的方法与设备

Also Published As

Publication number Publication date
CN108377356B (zh) 2020-07-28
US20200351471A1 (en) 2020-11-05
US11196962B2 (en) 2021-12-07
CN108377356A (zh) 2018-08-07
JP2021512562A (ja) 2021-05-13

Similar Documents

Publication Publication Date Title
WO2019141084A1 (zh) 基于虚拟画像的视频通话的方法与设备
US11997423B1 (en) Altering undesirable communication data for communication sessions
US11563739B2 (en) Authenticating a user device via a monitoring device
US11811827B2 (en) Securing endpoints for virtual meetings
JP6131248B2 (ja) 疎結合コンポーネントを使用した音声認識
WO2022262606A1 (zh) 活体检测方法、装置、电子设备和存储介质
US10348725B2 (en) Method of instant sharing invoked from wearable devices
US10534429B2 (en) Method of instant sharing invoked from wearable devices
US10298690B2 (en) Method of proactive object transferring management
WO2015176287A1 (zh) 应用文本信息进行通信的方法及装置
CN108141445A (zh) 用于人员重新识别的系统和方法
US9769434B1 (en) Remote control of a user's wearable computing device in help desk applications
US20200162698A1 (en) Smart contact lens based collaborative video conferencing
CN111382241A (zh) 会话场景切换方法及装置
US20170286755A1 (en) Facebot
US12335660B2 (en) Facilitating avatar modifications for learning and other videotelephony sessions in advanced networks
WO2021057644A1 (zh) 拍摄方法和装置
US10249295B2 (en) Method of proactive object transferring management
US20160285924A1 (en) Communication channel creation using sound stream
US11830120B2 (en) Speech image providing method and computing device for performing the same
TWI581626B (zh) 影音自動處理系統及方法
CN115884088A (zh) 一种设备位置信息的确定方法、装置及电子设备
US12444419B1 (en) Method and apparatus for generating text from audio
US12424239B2 (en) System and method for acoustic channel identification-based data verification
US12418514B2 (en) Computer-based privacy protection for chat groups in a virtual environment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18901061

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020560531

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 22/10/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18901061

Country of ref document: EP

Kind code of ref document: A1