Method and related device for quickly generating short videos based on 3D scenes

By using 3D scenes to generate short videos in the field of home decoration design, the problems of high cost and poor results are solved, and the creation of short videos with low cost and all-round display is achieved, meeting the diversified needs of end users.

CN114286197BActive Publication Date: 2024-11-15SHENZHEN BINCENT TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210001392.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-04
Publication Date
2024-11-15
Estimated Expiration
2042-01-04

AI Technical Summary

Technical Problem

The existing short video shooting cost in the field of home decoration design is high and the display effect is poor, which cannot meet the diversified needs of end users.

Method used

By obtaining 3D scene information, depicting the action path of the short video, dividing the video material into keyframe points, and setting camera position, angle and field of view data, obtaining the rendered pictures of each frame, combining them into target short videos, and reducing shooting Cost to meet diversified needs.

Benefits of technology

It effectively reduces the cost of short video shooting, can fully display the home decoration design effect, and meets the diversified short video creation needs of end users.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114286197B_ABST
    Figure CN114286197B_ABST
Patent Text Reader

Abstract

The present application is applicable to the computer field, and provides a method and related device for quickly generating short videos based on 3D scenes, including: obtaining 3D scene information, where the 3D scene information is a 3D scene constructed by a rendering engine; describing the action path of the short video to be recorded to obtain the original video material; dividing the original video material into a certain number of key frame points, setting jump information from each key frame point to the next key frame point, where the jump information includes jump duration and rendering information; obtaining a rendered image of each key frame point in the current 3D scene; merging all rendered images to obtain a target short video based on the 3D scene. The method of quickly generating short videos based on 3D scenes of the present application can quickly generate short videos based on 3D scenes, which can not only ensure the continuity between key frame points, but also meet the diversified needs of terminal users.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of video processing technology, and in particular, relates to a method and related device for quickly generating short videos based on 3D scenes. Background Art

[0002] With the development of computer technology and communication technology, the era of short videos has quietly arrived, and people can obtain information and resources through short videos. No matter which industry it is, everyone hopes to seize the traffic dividend brought by the short video era, and efficiently promote user conversion and realize traffic monetization within the short video system. In the interior design and home decoration industry, there is also a need for short videos showing home decoration design to better convert and communicate content.

[0003] Existing short videos in the field of home decoration design are all shot in real scenes or spliced ​​together by picture jumps; short videos shot in real scenes, whether they are artificial equipment or scene construction, increase the shooting cost of short videos; and the video spliced ​​together by picture jumps, the display effect cannot keep up with the rhythm of the current short video era, and the short video spliced ​​by image cannot fully display the effect of home decoration design, and cannot meet the diversified needs of end users. Summary of the invention

[0004] The purpose of this application is to provide a method and related devices for quickly generating short videos based on 3D scenes, aiming to solve the technical problems in the prior art of high short video shooting costs, poor display effects and inability to meet the diverse needs of end users.

[0005] The first aspect of the present application provides a method for quickly generating a short video based on a 3D scene, comprising:

[0006] Acquire 3D scene information, where the 3D scene information is a 3D scene constructed by a rendering engine;

[0007] Describe the action path of the short video you want to record and obtain the original video material;

[0008] The original video material is divided into a certain number of key frame points, and jump information from the key frame point of each frame to the key frame point of the next frame is set, wherein the jump information includes jump duration and rendering information;

[0009] Obtaining a rendered image of each key frame point in the current 3D scene;

[0010] All the rendered images are combined to obtain a target short video based on the 3D scene.

[0011] Optionally, after dividing the original video material into a certain number of key frame points, the method further includes:

[0012] Determine the key frame point of a certain frame that needs to be set;

[0013] Determine whether the camera position, angle and field of view angle data of the key frame point meet the requirements;

[0014] If the requirements are met, the rendered image of the key frame point is output;

[0015] If the requirements are not met, the camera position, angle and field of view angle data of the key frame points are further set.

[0016] Optionally, the setting of jump information from the key frame position of each frame to the key frame position of the next frame, wherein the jump information includes jump duration and rendering information, includes:

[0017] Set the jump duration from the key frame point of each frame to the key frame point of the next frame;

[0018] Calculate the difference in camera position, angle and field of view angle data between two key frame points;

[0019] The number of frames and camera information to be rendered are calculated by uniformly differencing the jump duration between the key frame points and the difference information of the camera position, angle and field of view angle data.

[0020] Optionally, the number of frames required to be rendered and the camera information may be automatically set or may be set according to actual needs.

[0021] Optionally, before merging all the rendered images to obtain a target short video based on a 3D scene, the method further includes:

[0022] Get recommended templates for video materials;

[0023] Replace the material information in the material recommendation template with the rendered image;

[0024] The target short video after replacement is obtained.

[0025] Optionally, after replacing the material information in the material recommendation template and the rendered image, the method further includes:

[0026] For the replaced target short video, the number of frames of the key frame points corresponding to the target short video and the information of the rendered image are determined according to the start and end time of the target short video.

[0027] Optionally, the material information in the video material recommendation template includes audio, video and picture background.

[0028] The second aspect of the present application provides a device for quickly generating a short video based on a 3D scene, comprising:

[0029] An information acquisition unit, used to acquire 3D scene information, wherein the 3D scene information is a 3D scene constructed by a rendering engine;

[0030] A path construction unit is used to describe the action path of the short video to be recorded and obtain the original video material;

[0031] A video analysis unit, used to divide the original video material into a certain number of key frame points, and set jump information from the key frame point of each frame to the key frame point of the next frame, wherein the jump information includes jump duration and rendering information;

[0032] A video editing unit, used for obtaining a rendered image of each key frame point in the current 3D scene;

[0033] The video generation unit is used to merge all the rendered images to obtain a target short video based on the 3D scene.

[0034] A third aspect of the present application provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for quickly generating short videos based on 3D scenes as described above.

[0035] In a fourth aspect, the present application provides a computer device having a storage medium storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for quickly generating short videos based on 3D scenes as described above.

[0036] The method for quickly generating short videos based on 3D scenes provided by the present application comprises the following steps: obtaining 3D scene information, wherein the 3D scene information is a 3D scene constructed by a rendering engine; describing the action path of the short video to be recorded to obtain the original video material; dividing the original video material into a certain number of key frame points, setting jump information from the key frame points of each frame to the key frame points of the next frame, wherein the jump information includes jump duration and rendering information; obtaining a rendered image of the key frame points of each frame in the current 3D scene; merging all the rendered images to obtain a target short video based on the 3D scene, thereby effectively reducing the cost of shooting short videos in the field of home improvement design, being able to fully display the graphic image effects in home improvement design, and being able to meet the diversified short video creation needs of terminal users. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1This is a flow chart of an embodiment of a method for quickly generating short videos based on 3D scenes in the present application;

[0038] Figure 2 This is another embodiment of the method for quickly generating a short video based on a 3D scene in the present application;

[0039] Figure 3 This is a flowchart of key frame point setting of an embodiment of the method for quickly generating a short video based on a 3D scene of the present application;

[0040] Figure 4 This is another embodiment of the method for quickly generating a short video based on a 3D scene in the present application;

[0041] Figure 5 This is a schematic diagram of an application environment of an embodiment of the method for quickly generating short videos based on 3D scenes of the present application;

[0042] Figure 6 is a schematic diagram of the device structure provided in an embodiment of the present application;

[0043] Figure 7 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0044] Figure 8 It is a schematic diagram of the structure of the server provided in the embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0047] As will be appreciated by those skilled in the art, the term "device" as used herein includes both wireless signal receiver devices, which are devices that only have a transmitting signal receiver without transmitting capability, and transmitting and receiving hardware devices, which are devices that have receiving and transmitting hardware capable of performing two-way communications over a two-way communications link. Such devices may include: cellular or other communications devices, which have a single line display or a multi-line display or a cellular or other communications device without a multi-line display; a PCS (Personal Communications Service), which may combine voice, data processing, fax and / or data communications capabilities; a PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar and / or a GPS (Global Positioning System) receiver; a conventional palmtop computer or other device, which has and / or includes a conventional laptop and / or palmtop computer or other device with and / or including a radio frequency receiver.

[0048] like Figure 1 and Figure 5 The figure is a flow chart of an embodiment of a method for quickly generating short videos based on 3D scenes.

[0049] In this embodiment, the method for quickly generating a short video based on a 3D scene includes:

[0050] S1000, obtaining 3D scene information, where the 3D scene information is a 3D scene constructed by a rendering engine;

[0051] The 3D scene information in this embodiment is a 3D scene constructed by a rendering engine, that is, obtained by 3D scene production software. The 3D scene information includes the creation, rendering and animation functions of a three-dimensional scene.

[0052] The three-dimensional scenes mainly include the internal and external structures of buildings in the field of home decoration design, the decoration design of buildings, and the furniture inside buildings.

[0053] S2000, describing the action path of the short video to be recorded, and obtaining the original video material;

[0054] The 3D scene can be switched automatically or manually, such as by clicking or sliding to switch the 3D scene, and selecting the part of the 3D scene to be displayed, and zooming in and out can be performed as needed.

[0055] In this embodiment, the terminal user can describe the action path of the short video he wants to record according to his own ideas and actual needs, and can move, rotate, scale, copy, delete and hide display objects in the 3D scene, and perform two-handed interaction in VR mode to obtain the original video material.

[0056] S3000, dividing the original video material into a certain number of key frame points, setting jump information from the key frame point of each frame to the key frame point of the next frame, wherein the jump information includes jump duration and rendering information;

[0057] The key frame in this embodiment refers to the frame where the key action is located during the scene movement change process during the switching of the 3D scene. After obtaining the original video material, it is divided into a certain number of key frame points, and further set the jump information from the key frame point of each frame to the key frame point of the next frame.

[0058] The jump information includes jump duration and rendering information, and the jump information can be set automatically or manually. The rendering information is rendered by a renderer, and during the rendering process, the rendering parameters can be based on the home decoration design information in the 3D scene, wherein the rendering parameters mainly include reflection subdivision, refraction subdivision, light subdivision, light shadow, maximum depth, etc., which are not limited here.

[0059] S4000, obtaining a rendering image of each key frame point in the current 3D scene;

[0060] In this embodiment, after rendering is completed, a rendered image of each key frame point in the current 3D scene can be obtained.

[0061] S5000: Merge all the rendered images to obtain a target short video based on the 3D scene.

[0062] All the rendered images are merged, and the transition frames between the key frame points of each frame are created and added by the software to obtain a target short video based on the 3D scene.

[0063] The method for quickly generating short videos based on 3D scenes provided in the embodiments of the present application obtains 3D scene information, depicts the action path of the short video to be recorded, obtains the original video material, divides the original video material into a certain number of key frame points, and obtains a rendered image of each key frame point in the current 3D scene; merges all the rendered images to obtain a target short video based on the 3D scene, effectively reducing the cost of shooting short videos in the field of home improvement design, can fully display the graphic image effects in home improvement design, and can meet the diversified short video creation needs of terminal users.

[0064] like Figure 2 , which is a flow chart of another embodiment of a method for quickly generating short videos based on 3D scenes.

[0065] In this embodiment, after the original video material is divided into a certain number of key frame points, the method further includes:

[0066] S2100, determining a key frame point of a certain frame to be set;

[0067] S2200, determining whether the camera position, angle, and field of view angle data of the key frame point meet the requirements;

[0068] In this embodiment, the camera position, angle and field of view data of the key frame points can be determined according to the actual needs of the terminal user, and the terminal user can move, rotate, scale, copy, delete and hide displayed objects in the 3D scene.

[0069] S2300: If the requirements are met, output the rendered image of the key frame point;

[0070] S2400: If the requirements are not met, further set the camera position, angle and field of view angle data of the key frame point.

[0071] This embodiment first determines the key frame point of a certain frame that needs to be set, and then determines whether the camera position, angle and field of view angle data of the key frame point meet the requirements. The terminal user can move, rotate, scale, copy, delete and hide display objects in the 3D scene, so that the camera position, angle and field of view angle data of the key frame point can meet the requirements, and then outputs the rendered image of the key frame point.

[0072] The embodiments of the present application can meet the different needs of different terminal users when creating short videos. Terminal users can reasonably select partial scenes of home decoration design according to their preferences and move, rotate and scale them, etc., which can meet the diversified short video creation needs of terminal users.

[0073] like Figure 3 The figure is a flowchart of key frame point setting of an embodiment of the method for quickly generating short videos based on 3D scenes of the present application.

[0074] In this embodiment, the jump information from the key frame point of each frame to the key frame point of the next frame is set, and the jump information includes the jump duration and rendering information, including:

[0075] S3100, setting the jump duration from the key frame point of each frame to the key frame point of the next frame;

[0076] S3200, calculating the difference in camera position, angle and field of view angle data between two key frame points;

[0077] S3300, calculate the number of frames and camera information that need to be rendered by uniformly differencing according to the jump duration between the key frame points and the difference information of the camera position, angle and field of view angle data.

[0078] In order to speed up the rendering speed and save the rendering time, in this embodiment, the jump information from the key frame point of each frame to the key frame point of the next frame is processed by a uniform difference method.

[0079] Manually set the jump duration from the key frame point of each frame to the key frame point of the next frame, and then calculate the difference in camera position, angle and field of view angle data between the two key frame points. According to the jump duration between the key frame points and the difference information of the camera position, angle and field of view angle data, the number of frames and camera information to be rendered are calculated by uniform difference.

[0080] The embodiment of the present application adopts a uniform difference method for processing, which effectively improves the rendering and processing efficiency of short videos, and at the same time can ensure the visual change effect of the image when the key frame point of each frame jumps to the key frame point of the next frame, so as to meet the needs of end users.

[0081] like Figure 4 , which is a flow chart of another embodiment of a method for quickly generating short videos based on 3D scenes.

[0082] In this embodiment, in order to meet the short video creation needs of terminal users and save time in creating short videos, a video quick-cut recommended template is further introduced to make the creation of short videos more concise and efficient.

[0083] Before merging all the rendered images to obtain a target short video based on a 3D scene, the method further includes:

[0084] S4100, obtaining a recommended template for video material;

[0085] S4200, replacing the material information in the material recommendation template and the rendered image;

[0086] S4300: Obtain the target short video after replacement.

[0087] This embodiment obtains a video material recommendation template, which includes material information. The material information may be one or more of audio, video, and picture background. The material information in the material recommendation template and the rendered picture are replaced to obtain a target video.

[0088] Furthermore, the method further comprises:

[0089] S4400. For the replaced target short video, determine the number of frames of the key frame points and the information of the rendered image corresponding to the target short video according to the start and end time of the target short video.

[0090] In this embodiment, the material information contained in the video material recommendation template, such as the video and picture background, is replaced by the original video material, thereby enabling self-editing and creation.

[0091] At the same time, according to the start and end time of the target short video, the frame number of the key frame points corresponding to the target short video and the information of the rendered image are determined to ensure that the jump from the key frame points of each frame to the key frame points of the next frame can present a perfect effect.

[0092] The method for quickly generating short videos based on 3D scenes provided in the embodiment of the present application can meet the short video creation needs of terminal users, ensure the quality and efficiency of short video creation, and enable the short videos created by terminal users based on 3D scenes to be perfectly presented.

[0093] like Figure 6 As shown, the present application also provides a device for quickly generating short videos based on 3D scenes, including:

[0094] An information acquisition unit, used to acquire 3D scene information, wherein the 3D scene information is a 3D scene constructed by a rendering engine;

[0095] A path construction unit is used to describe the action path of the short video to be recorded and obtain the original video material;

[0096] A video analysis unit, used to divide the original video material into a certain number of key frame points, and set jump information from the key frame point of each frame to the key frame point of the next frame, wherein the jump information includes jump duration and rendering information;

[0097] A video editing unit, used for obtaining a rendered image of each key frame point in the current 3D scene;

[0098] The video generation unit is used to merge all the rendered images to obtain a target short video based on the 3D scene.

[0099] Since the above-mentioned device for quickly generating short videos based on 3D scenes is a device that corresponds one-to-one to the method for quickly generating short videos based on 3D scenes, its implementation principle is the same as that of the method for quickly generating short videos based on 3D scenes, and will not be repeated here.

[0100] In this embodiment, please refer to Figure 7, provides a basic structural block diagram of computer equipment.

[0101] The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected via a system bus. The non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a method for quickly generating short videos based on 3D scenes. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute a method for quickly generating short videos based on 3D scenes. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1001 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, processor 1001 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0103] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the method for quickly generating short videos based on 3D scenes as described in any of the above embodiments.

[0104] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one instruction, which is used to be executed by the processor to implement the method for quickly generating a short video based on a 3D scene provided in the method embodiment of the present application.

[0105] like Figure 8 A schematic diagram of the structure of a server provided in one embodiment of the present application is shown. The server is used to implement the method for quickly generating short videos based on 3D scenes provided in the above embodiment. Specifically:

[0106] The server includes a central processing unit (CPU), a system memory including a random access memory (RAM) and a read-only memory (ROM), and a system bus connecting the system memory and the central processing unit. The server also includes a basic input / output system (I / O system) that helps transfer information between various components in the computer, and a large-capacity storage device for storing an operating system, application programs, and other program modules.

[0107] The basic input / output system includes a display for displaying information and an input device such as a mouse and a keyboard for a user to input information. The display and the input device are connected to the central processing unit through an input / output controller connected to the system bus. The basic input / output system may also include an input / output controller for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus.

[0108] The mass storage device is connected to the central processing unit via a mass storage controller (not shown) connected to the system bus. The mass storage device and its associated computer readable medium provide non-volatile storage for the server. That is, the mass storage device may include a computer readable medium (not shown) such as a hard disk or a CD-ROM drive.

[0109] Without loss of generality, the computer readable medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storage technologies, CD-ROM, DVD or other optical storage, cassettes, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the above. The above-mentioned system memory and mass storage devices may be collectively referred to as memory.

[0110] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0111] The embodiments of the present invention are each process and / or box in the process and / or box in the flowchart and / or box diagram of the method, terminal device (system) and computer program product according to the embodiments of the present invention, and the combination of the process and / or box in the flowchart and / or box diagram. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the process. Figure 1 A device that specifies the functions in one or more blocks in a process or multiple processes and / or a block diagram.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified by a box or boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] In addition, each functional device in each embodiment of the present invention may be integrated into the same data processing device, or each device may exist physically separately, or two or more devices may be integrated into the same device.

[0115] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other devices or steps, and the singular does not exclude the plural. Multiple devices or computer devices stated in the computer device claim can also be implemented by the same computer device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0116] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions or improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for quickly generating short videos based on 3D scenes, characterized in that: include: Acquire 3D scene information, where the 3D scene information is a 3D scene constructed by a rendering engine; Describe the action path of the short video you want to record and obtain the original video material; The original video material is divided into a certain number of key frame points, and jump information from the key frame point of each frame to the key frame point of the next frame is set, wherein the jump information includes jump duration and rendering information; Obtaining a rendered image of each key frame point in the current 3D scene; Merging all the rendered images to obtain a target short video based on the 3D scene; After the original video material is divided into a certain number of key frame points, the method further includes: Determine the key frame point of a certain frame that needs to be set; Determine whether the camera position, angle and field of view angle data of the key frame point meet the requirements; If the requirements are met, the rendered image of the key frame point is output; If the requirements are not met, the camera position, angle and field of view angle data of the key frame points are further set; The step of setting the jump information from the key frame position of each frame to the key frame position of the next frame includes: Set the jump duration from the key frame point of each frame to the key frame point of the next frame; Calculate the difference in camera position, angle and field of view angle data between two key frame points; The number of frames and camera information to be rendered are calculated by uniformly differencing the jump duration between the key frame points and the difference information of the camera position, angle and field of view angle data.

2. The method for quickly generating short videos based on 3D scenes as claimed in claim 1, characterized in that: Before merging all the rendered images to obtain a target short video based on a 3D scene, the method further includes: Get the recommended template for video material; The material information in the material recommendation template and the rendered image are replaced.

3. The method for quickly generating short videos based on 3D scenes as claimed in claim 2, characterized in that: After replacing the material information in the material recommendation template and the rendered image, the method further includes: For the replaced target short video, the number of frames of the key frame points corresponding to the target short video and the information of the rendered image are determined according to the start and end time of the target short video.

4. The method for quickly generating short videos based on 3D scenes as claimed in claim 2, characterized in that: The material information in the video material recommendation template includes audio, video and picture background.

5. A device for quickly generating short videos based on 3D scenes, characterized in that: include: An information acquisition unit, used to acquire 3D scene information, wherein the 3D scene information is a 3D scene constructed by a rendering engine; A path construction unit is used to describe the action path of the short video to be recorded and obtain the original video material; A video analysis unit, used to divide the original video material into a certain number of key frame points, and set jump information from the key frame point of each frame to the key frame point of the next frame, wherein the jump information includes jump duration and rendering information; A video editing unit, used for obtaining a rendered image of each key frame point in the current 3D scene; A video generation unit, used for merging all the rendered images to obtain a target short video based on the 3D scene; The video analysis unit is also used to: after dividing the original video material into a certain number of key frame points, determine the key frame point of a certain frame that needs to be set; Determine whether the camera position, angle and field of view angle data of the key frame point meet the requirements; If the requirements are met, the rendered image of the key frame point is output; If the requirements are not met, the camera position, angle and field of view angle data of the key frame points are further set; The step of setting the jump information from the key frame position of each frame to the key frame position of the next frame includes: Set the jump duration from the key frame point of each frame to the key frame point of the next frame; Calculate the difference in camera position, angle and field of view angle data between two key frame points; The number of frames and camera information to be rendered are calculated by uniformly differencing the jump duration between the key frame points and the difference information of the camera position, angle and field of view angle data.

6. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the method for quickly generating short videos based on 3D scenes as described in any one of claims 1 to 4.

7. A storage medium storing computer-readable instructions, which, when executed by one or more processors, enables the one or more processors to perform the steps of the method for quickly generating short videos based on 3D scenes as described in any one of claims 1 to 4.