Method and apparatus for processing three-dimensional video, readable storage medium and electronic device

Patent metadata

Field	Value
Publication number	US-2022417486-A1
Application number	US-202217885323-A
Country	US
Kind code	A1
Filing date	Aug 10, 2022
Priority date	Mar 27, 2020
Publication date	Dec 29, 2022
Grant date	—

Abstract

A method and an apparatus for processing a three-dimensional video, a readable storage medium and an electronic device are involved in the present disclosure, and the present disclosure relates to the field of electronic information technologies. The method is applied to a terminal device, and includes: sending an initial two-dimensional image to a server, so that the server generates an initial three-dimensional video according to the initial two-dimensional image; receiving the initial three-dimensional video sent by the server, and processing the initial three-dimensional video to obtain a target three-dimensional video. According to the present disclosure, a two-dimensional image on the terminal device is uploaded to the server and is converted into a three-dimensional video by the server, then the three-dimensional video is processed by the terminal device.

First claim

What is claimed is:

1 . A method for processing a three-dimensional video, applied to a terminal device, wherein the method comprises:
sending at least one initial two-dimensional image to a server, which enables the server to generate an initial three-dimensional video according to the at least one initial two-dimensional image; receiving the initial three-dimensional video sent by the server; and performing processing on the initial three-dimensional video to obtain a target three-dimensional video.

2 . The method according to claim 1 , wherein the performing processing on the initial three-dimensional video to obtain the target three-dimensional video comprises:
decoding the initial three-dimensional video according to decoding parameters to obtain an initial image frame set of the initial three-dimensional video; and performing processing on the initial image frame set according to configuration parameters to obtain the target three-dimensional video.

3 . The method according to claim 2 , wherein the configuration parameters comprise at least one of the following parameters: rendering parameters and splicing parameters, and the performing processing on the initial image frame set according to the configuration parameters to obtain the target three-dimensional video comprises:
performing rendering on at least one initial image frame in the initial image frame set according to the rendering parameters to obtain the rendered image frame set, and performing splicing on image frames in the rendered image frame set according to the splicing parameters to obtain the target three-dimensional video; or, performing rendering on at least one initial image frame in the initial image frame set according to the rendering parameters to obtain the target three-dimensional video; or, performing splicing on initial image frames in the initial image frame set according to the splicing parameters to obtain the target three-dimensional video.

4 . The method according to claim 3 , wherein the performing processing on the initial three-dimensional video to obtain the target three-dimensional video further comprises:
determining at least one of a rendering space and a time axis; the performing processing on the initial image frame set according to the configuration parameters to obtain the target three-dimensional video comprises: according to the rendering parameters, performing rendering on the at least one initial image frame in the initial image frame set in the rendering space to obtain the rendered image frame set, and according to a time sequence indicated by the time axis, performing splicing on the image frames in the rendered image frame set according to the splicing parameters to obtain the target three-dimensional video; or, performing rendering on the at least one initial image frame in the initial image frame set in the rendering space according to the rendering parameters to obtain the target three-dimensional video; or, according to an indication of the time axis, performing splicing on the initial image frames in the initial image frame set according to the splicing parameters to obtain the target three-dimensional video.

5 . The method according to claim 1 , wherein before the sending the at least one initial two-dimensional image to the server, the method further comprises:
acquiring a target model according to the received model selecting instruction, wherein the model selecting instruction comprises target model information for indicating the target model; determining image parameters comprised in the target model; and determining the at least one initial two-dimensional image which matches the image parameters.

6 . The method according to claim 5 , wherein the acquiring the target model according to the received model selecting instruction comprises:
in response to the model selecting instruction, searching the terminal device for the target model corresponding to the target model information; when the target model does not exist on the terminal device, sending a request to the server, which enables the server to determine and send the target model; and receiving the target model sent by the server.

7 . The method according to claim 2 , wherein after the decoding the initial three-dimensional video according to the decoding parameters to obtain the initial image frame set of the initial three-dimensional video, the performing processing on the initial three-dimensional video to obtain the target three-dimensional video further comprises:
determining a display order of each initial image frame in the initial image frame set according to a preset rule; and the performing processing on the initial image frame set according to the configuration parameters to obtain the target three-dimensional video comprises: according to the configuration parameters, performing processing on the initial image frames in the initial image frame set according to the display order to obtain the target three-dimensional video.

8 . A method for processing a three-dimensional video, applied to a server, wherein the method comprises:
receiving at least one initial two-dimensional image sent by a terminal device, and generating an initial three-dimensional video according to the at least one initial two-dimensional image; and sending the initial three-dimensional video to the terminal device, which enables the terminal device to perform processing on the initial three-dimensional video to obtain a target three-dimensional video.

9 . The method according to claim 8 , wherein before the receiving the initial two-dimensional image sent by the terminal device, the method further comprises:
receiving a request sent by the terminal device, wherein the request is a request sent by the terminal device when no target model exists on the terminal device; in response to the request, acquiring a target model comprising image parameters; and sending the target model to the terminal device, which enables the terminal device to determine the at least one initial two-dimensional image which matches the image parameters.

10 . A non-transitory computer readable storage medium, on which a computer program is stored, wherein the program is configured to implement the method according to claim 1 when being executed by a processor.

11 . A non-transitory computer readable storage medium, on which a computer program is stored, wherein the program is configured to implement the method according to claim 8 when being executed by a processor.

12 . An electronic device, comprising:
a memory, on which a computer program is stored; and a processor, configured to execute the computer program stored in the memory, so as to: send at least one initial two-dimensional image to a server, which enables the server to generate an initial three-dimensional video according to the at least one initial two-dimensional image; receive the initial three-dimensional video sent by the server; and perform processing on the initial three-dimensional video to obtain a target three-dimensional video.

13 . The electronic device according to claim 12 , wherein the processor is further execute the computer program stored in the memory, so as to:
decode the initial three-dimensional video according to decoding parameters to obtain an initial image frame set of the initial three-dimensional video; and perform processing on the initial image frame set according to configuration parameters to obtain the target three-dimensional video.

14 . The electronic device according to claim 13 , wherein the configuration parameters comprise at least one of

Assignees

• Beijing Bytedance Network Tech Co Ltd

Inventors

• Zhang Shupeng
• Li Yameng
• Li Ziyu
• Yang Ningfei
• Liu Sixue

Classifications

• H04N21/816 Primary

  involving special video data, e.g 3D video · CPC title

• H04N13/161

  Encoding, multiplexing or demultiplexing different image signal components (for multi-view video sequence encoding H04N19/597) · CPC title

• H04N13/261

  with monoscopic-to-stereoscopic image conversion · CPC title

• H04N13/122

  Improving the three-dimensional [3D] impression of stereoscopic images by modifying image signal contents, e.g. by filtering or adding monoscopic depth cues (H04N13/128 takes precedence) · CPC title

• H04N13/106 Primary

  Processing image signals (for multi-view video sequence encoding H04N19/597) · CPC title