Video processing method, apparatus and device

Patent metadata

Field	Value
Publication number	US-2024177374-A1
Application number	US-202218551967-A
Country	US
Kind code	A1
Filing date	Mar 21, 2022
Priority date	Apr 9, 2021
Publication date	May 30, 2024
Grant date	—

Abstract

Embodiments of the present disclosure provide a video processing method, an apparatus and a device. The method includes: receiving a video generating request; acquiring a video template according to the video generating request, where the video template includes a plurality of placeholders, where each of the placeholders is configured to indicate at least one of a text type, an image type and a video type; acquiring a plurality of materials according to the video generating request, where types of the plurality of the materials include at least one of a text type, an image type and a video type; based on the types of the materials, importing the plurality of the materials into positions of corresponding placeholders in the video template respectively and performing rendering to obtain a synthesized video.

First claim

What is claimed is:

1 . A video processing method, wherein the method comprises:
receiving a video generating request; acquiring a video template according to the video generating request, wherein the video template comprises a plurality of placeholders, wherein each of the placeholders is configured to indicate at least one of a text type, an image type and a video type; acquiring a plurality of materials according to the video generating request, wherein types of the plurality of the materials comprise at least one of a text type, an image type and a video type; and based on the types of the materials, importing the plurality of the materials into positions of corresponding placeholders in the video template respectively and performing rendering to obtain a synthesized video.

2 . The method according to claim 1 , wherein the materials comprise first type tags and the placeholders comprise second type tags;
wherein based on the types of the materials, importing the plurality of the materials into the positions of the corresponding placeholders in the video template respectively and performing the rendering to obtain the synthesized video comprises: screening out a target material and a target placeholder with a first type tag of the target material being consistent with a second type tag of the target placeholder; importing the target material into a position of the target placeholder in the video template after pre-processing the target material; rendering an image frame of the video template with the target material imported so as to obtain the synthesized video.

3 . The method according to claim 2 , wherein importing the target material into the position of the target placeholder in the video template after pre-processing the target material comprises:
upon determining that the target material comprises a text material, importing the text material into the position of the target placeholder in the video template after performing processing of typesetting and texture format conversion on the text material; upon determining that the target material comprises an image material, importing the image material into the position of the target placeholder in the video template after performing processing of texture format conversion on the image material; upon determining that the target material comprises a video material, extracting an image frame from the video material, and importing the extracted image frame into the position of the target placeholder in the video template after performing processing of texture format conversion on the extracted image frame.

4 . The method according to claim 3 , wherein extracting the image frame from the video material comprises:
determining a first start timestamp and a first end timestamp of the video material in a to-be-synthesized video; determining a second start timestamp and a second end timestamp indicated by the target placeholder; calculating a target timestamp of an image frame to be extracted from the video material according to a timestamp of a current rendered frame of the to-be-synthesized video, the first start timestamp, the first end timestamp, the second start timestamp and the second end timestamp; extracting the image frame from the video material according to the target timestamp.

5 . The method according to claim 4 , wherein calculating the target timestamp of the image frame to be extracted from the video material according to the timestamp of the current rendered frame of the to-be-synthesized video, the first start timestamp, the first end timestamp, the second start timestamp and the second end timestamp comprises:
acquiring a time length indicated by the placeholder according to the second end timestamp and the second start timestamp; acquiring a proportional time length of the target timestamp located in the video material according to a product of the time length indicated by the placeholder and a ratio of a difference between the timestamp of the current rendered frame and the first start timestamp to a difference between the first end timestamp and the first start timestamp; acquiring the target timestamp according to the second start timestamp and the proportional time length of the target timestamp to the video material.

6 . The method according to claim, wherein extracting the image frame from the video material according to the target timestamp comprises:
upon determining that a time length of the video material is less than a time length indicated by the placeholder corresponding to the video material in the video template, continuing image frame extraction from a starting point of the video material again.

7 . The method according to any one of claim 2 , wherein rendering the image frame of the video template with the target material imported comprises:
identifying a renderer corresponding to the target placeholder in the video template; rendering, according to a rendering effect of the renderer, the image frame of the video template with the target material imported.

8 . The method according to any one of claim 1 , before receiving the video generating request, further comprising:
acquiring a video template producing material, wherein the video template producing material comprises at least one of a rendering material and a cutscene animation; pre-adding the plurality of the placeholders; producing the video template according to the video template producing material and the pre-added plurality of the placeholders.

9 . A video processing apparatus, wherein the apparatus comprises:
a processor and a memory; wherein the memory stores computer execution instructions; the processor executes the computer execution instructions to cause the processor to: receive a video generating request; acquire a video template according to the video generating request, wherein the video template comprises a plurality of placeholders, wherein each of the placeholders is configured to indicate at least one of a text type, an image type and a video type; acquire a plurality of materials according to the video generating request, wherein types of the plurality of the materials comprise at least one of a text type, an image type and a video type; based on the types of the materials, import the plurality of the materials into positions of corresponding placeholders in the video template respectively and perform rendering to obtain a synthesized video.

10 . (canceled)

11 . A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the processor executes steps of:
receiving a video generating request; acquiring a video template according to the video generating request, wherein the video template comprises a plurality of placeholders, wherein each of the placeholders is configured to indicate at least one of a text type, an image type and a video type; acquiring a plurality of materials according to the video generating request, wherein types of the plurality of the materials comprise at least one of a text type, an image type and a video type; and based on the types of the materials, importing the plurality of the materials into positions of corresponding placeholders in the video template respectively and performing rendering to obtain a synthesized video.

12 - 13 . (canceled)

14 . The method according to claim 5 , wherein extracting the image frame from the video material according to the target timestamp comprises:
upon determining that a time length of the video material is less than a time leng

Assignees

• Beijing Zitiao Network Technology Co Ltd

Inventors

• ZhuGe Jingjing
• Li Ziyu
• Shen Yanhao
• Ni Guangyao

Classifications

• G06T11/10 Primary

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06T11/001 Primary

  Physics · mapped topic

• G06T2210/32

  Image data format · CPC title

• H04N21/44012 Primary

  involving rendering scenes according to scene graphs, e.g. MPEG-4 scene graphs · CPC title

• H04N21/458

  Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules {; time-related management operations (arrangements for replacing or switching information during the broadcast or during the distribution H04H20/10)} · CPC title