WO2024212310A1 - 一种三维动画渲染加速方法及系统 - Google Patents

一种三维动画渲染加速方法及系统 Download PDF

Info

Publication number
WO2024212310A1
WO2024212310A1 PCT/CN2023/095119 CN2023095119W WO2024212310A1 WO 2024212310 A1 WO2024212310 A1 WO 2024212310A1 CN 2023095119 W CN2023095119 W CN 2023095119W WO 2024212310 A1 WO2024212310 A1 WO 2024212310A1
Authority
WO
WIPO (PCT)
Prior art keywords
resolution
animation
rendering
frame
low
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/CN2023/095119
Other languages
English (en)
French (fr)
Inventor
郭家琪
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to US18/263,542 priority Critical patent/US20260105669A1/en
Priority to CA3206104A priority patent/CA3206104A1/en
Priority to EP23744350.2A priority patent/EP4468247A4/en
Publication of WO2024212310A1 publication Critical patent/WO2024212310A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T13/00—Animation
    • G06T13/20—Three-dimensional [3D] animation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
    • H04N21/440263—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by altering the spatial resolution, e.g. for displaying on a connected PDA
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—Three-dimensional [3D] image rendering
    • G06T15/005—General purpose rendering architectures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H04N21/234363—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by altering the spatial resolution, e.g. for clients with a lower screen resolution
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H04N21/23439—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements for generating different versions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
    • H04N21/440281—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by altering the temporal resolution, e.g. by frame skipping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/816—Monomedia components thereof involving special video data, e.g 3D video
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present invention relates to the field of animation rendering technology, and in particular to a three-dimensional animation rendering acceleration method and system.
  • the methods that can speed up rendering in the 3D animation rendering process include: 1. Replace the 3D renderer 2. Improve computer configuration 3. Optimize rendering settings 4. Cooperate with third-party rendering farms 5. Replace 3D software, etc.
  • the existing methods of accelerating rendering require more investment, more time and energy to optimize rendering settings according to lens and scene requirements, and more learning time costs.
  • the purpose of the present invention is to provide a 3D animation rendering acceleration method and system, which obtains a low-resolution or/and low-frame-rate 3D animation by reducing the resolution and/or frame rate of the 3D animation to be rendered; starts the corresponding AI function in a renderer with built-in AI super-resolution and frame-filling functions, performs AI super-resolution and AI frame-filling accelerated rendering on the pictures rendered by the low-resolution or/and low-frame-rate 3D animation, obtains the 3D animation sequence after accelerated rendering, and then completes other post-production, which can greatly reduce the rendering time of the conventional 3D animation, and solves the problem of the existing conventional 3D animation production process being modified due to the large-scale rendering of the 3D animation sequence.
  • the resulting repeated rendering requires a lot of effort, cost and wastes a lot of time.
  • an embodiment of the present application provides a method for accelerating three-dimensional animation rendering, comprising the following steps: obtaining a three-dimensional animation to be rendered; reducing the resolution and/or frame rate of the three-dimensional animation to be rendered to obtain a low-resolution and/or low-frame-rate three-dimensional animation; starting the corresponding AI function in a renderer with built-in AI super-resolution and frame insertion functions, starting rendering of the low-resolution and/or low-frame-rate three-dimensional animation and performing AI accelerated rendering to obtain a three-dimensional animation image sequence after accelerated rendering.
  • the specific steps of reducing the resolution and frame rate of the three-dimensional animation to be rendered include: in the dynamic animation rendering setting, reducing the resolution of the exported sequence frames to obtain a low-resolution three-dimensional animation; in the dynamic animation rendering setting, reducing the frame rate of the exported sequence frames to obtain a low-frame rate three-dimensional animation.
  • the steps of starting the corresponding AI function in a renderer with built-in AI super-resolution and frame interpolation functions, starting rendering of low-resolution and/or low-frame-rate three-dimensional animations and performing AI accelerated rendering specifically include: in the AI super-resolution tool, setting the resolution of the super-resolution target, and obtaining the AI super-resolution sequence frames after running; the AI super-resolution tool is pre-obtained based on deep learning technology through feature extraction, feature dimension transformation, nonlinear linking, mapping, deconvolution amplification, and neural network processing; importing the AI super-resolution sequence frames into the AI frame interpolation tool; in the AI frame interpolation tool, setting the target frame rate after frame interpolation, after the setting is completed, the AI frame interpolation tool generates an intermediate frame rate based on the previous and next frames based on the artificial intelligence algorithm, and interpolates frames according to the intermediate frame rate until the frame interpolation is completed; importing the sequence frames after the frame interpolation is completed
  • the intermediate frame rate can be infinitely divided to achieve any custom frame number.
  • an embodiment of the present application provides a three-dimensional animation rendering acceleration system, which includes: an acquisition module, used to acquire a three-dimensional animation to be rendered; a resolution and frame reduction module, used to reduce the resolution and/or frame rate of the three-dimensional animation to be rendered to obtain a low-resolution and/or low-frame-rate three-dimensional animation; an accelerated rendering module: used to start the corresponding AI function in a renderer with built-in AI super-resolution and frame supplementation functions, start rendering of the low-resolution and/or low-frame-rate three-dimensional animation and perform AI accelerated rendering to obtain a three-dimensional animation image sequence after accelerated rendering.
  • an embodiment of the present application provides an electronic device, comprising a memory for storing one or more programs; and a processor, which, when the one or more programs are executed by the processor, implements the method as described in any one of the first aspects.
  • an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of the above-mentioned first aspects.
  • the embodiments of the present invention have at least the following advantages or beneficial effects:
  • An embodiment of the present invention proposes a 3D animation rendering acceleration method, which obtains a low-resolution and/or low-frame-rate 3D animation by reducing the resolution and/or frame rate of the 3D animation to be rendered; starts the corresponding AI function in a renderer with built-in AI super-resolution and frame-interpolation functions, starts rendering the low-resolution and/or low-frame-rate 3D animation, and performs AI super-resolution and AI frame-interpolation accelerated rendering on the rendered images during the 3D animation rendering process, obtains the 3D animation sequence after accelerated rendering, and then completes other post-production, which can greatly reduce the rendering time of conventional 3D animation, and solves the problem that repeated rendering caused by modifications in the existing conventional 3D animation production process requires a lot of effort, cost and waste of time.
  • FIG1 is a flow chart of an embodiment of a method for accelerating 3D animation rendering according to the present invention
  • FIG2 is a flow chart of another embodiment of a 3D animation rendering acceleration method of the present invention.
  • FIG3 is a structural block diagram of an embodiment of a 3D animation rendering acceleration system according to the present invention.
  • FIG. 4 is a structural block diagram of an electronic device provided by an embodiment of the present invention.
  • Icons 1. Acquisition module; 2. Resolution reduction and frame reduction module; 3. Accelerated rendering module; 4. Processor; 5. Memory; 6. Data bus.
  • the embodiment of the present application provides a 3D animation rendering acceleration method.
  • the 3D animation rendering acceleration method includes the following steps:
  • Step S101 Obtain the 3D animation to be rendered.
  • the 3D animation to be rendered can be obtained by producing static storyboards of 3D animation and dynamic animation according to user needs.
  • the static storyboard production can be designed according to the user's animation script, and the 3D animation design software is used to create frames of animation images; then the obtained animation images are organized on the timeline according to the scene storyboards to produce dynamic animation.
  • Step S102 reducing the resolution and/or frame rate of the 3D animation to be rendered to obtain a low-resolution and/or low-frame-rate 3D animation.
  • the resolution and/or frame rate of the 3D animation to be rendered are reduced to obtain a low-resolution and/or low-frame-rate 3D animation.
  • the above-mentioned rendering parameters can be dynamically adjusted and set for the 3D animation to be rendered through the renderers provided by 3D software such as 3Dmax, Maya, C4D, Blender, or third-party renderers, so as to preliminarily obtain a 3D animation that meets the requirements.
  • AI super-resolution function modules and AI frame supplementation function modules in the renderers provided by 3D software such as 3Dmax, Maya, C4D, Blender, or third-party renderers to perform AI-assisted rendering on the 3D animation to improve rendering efficiency.
  • Step S103 Activate the corresponding AI function in the renderer with built-in AI super-resolution and frame interpolation functions, start rendering of low-resolution and/or low-frame-rate 3D animation and perform AI accelerated rendering to obtain a 3D animation picture sequence after accelerated rendering.
  • the AI super-resolution function uses deep learning technology, which can achieve the same level of image quality as the resolution while improving the resolution of the video through feature extraction, feature dimension transformation, nonlinear linking, mapping, deconvolution amplification and other processes, and after neural network processing.
  • the AI frame interpolation function uses artificial intelligence algorithms to calculate the intermediate frame rate based on the previous and next frames, and can also infinitely divide the intermediate frame to achieve any custom frame number.
  • the specific steps of reducing the resolution and frame rate of the three-dimensional animation to be rendered include: in the dynamic animation rendering setting, reducing the resolution of the exported sequence frames to obtain a low-resolution three-dimensional animation; in the dynamic animation rendering setting, reducing the frame rate of the exported sequence frames to obtain a low-frame rate three-dimensional animation.
  • the resolution and frame rate of the imported sequence frames are reduced to 50% or less of the target resolution and frame rate.
  • the steps of starting the corresponding AI function in a renderer with built-in AI super-resolution and frame interpolation functions, starting rendering of low-resolution and/or low-frame-rate 3D animations, and performing AI accelerated rendering specifically include:
  • the AI super-resolution tool in the AI super-resolution tool, setting the resolution of the super-resolution target, and obtaining the AI super-resolution sequence frame after running;
  • the AI super-resolution tool is pre-based on deep learning technology, through feature extraction, feature dimension transformation, non-linear linking, mapping, deconvolution amplification, and neural network processing;
  • the AI super-resolution function uses deep learning technology. Through feature extraction, feature dimension transformation, non-linear linking, mapping, deconvolution amplification and other processes, and after neural network processing, it can allow the video to obtain the same level of image quality as the target resolution while improving the resolution.
  • S204 In the AI interpolation tool, set the target frame rate after interpolation. After the setting is completed, the AI interpolation tool calculates the intermediate frame rate based on the previous and next frames based on the artificial intelligence algorithm, and interpolates frames according to the intermediate frame rate until the interpolation is completed; S205: Import the sequence frames after interpolation into the post-production synthesis software In the document, continue the post-production of 3D animation.
  • intermediate frame rates can be infinitely divided to achieve any custom frame number.
  • the above-mentioned AI frame interpolation function is used to interpolate frames for 3D animation and accelerate rendering. Based on the current common 3D animation frame rates (24 frames/second, 25 frames/second, 30 frames/second, 60 frames/second, etc.), by reducing the rendering frame rate to 12 to 15 frames/second, the rendering time can be shortened by about 50% to 80%, thereby further reducing the rendering time of conventional 3D animation.
  • the user can specifically turn on the AI super-resolution function, turn on the AI frame interpolation function 11, or turn on the AI super-resolution function and the AI frame interpolation function at the same time in the renderer to achieve AI accelerated rendering of 3D animation, which can shorten the overall rendering time of 3D animation by about 70% to 90%, thereby greatly reducing the rendering time of conventional 3D animation, solving the problem of repeated rendering caused by modifications in the existing conventional 3D animation production process, which requires a lot of energy, cost and waste of time, thereby achieving the purpose of improving rendering efficiency.
  • an embodiment of the present application provides a 3D animation rendering acceleration system, which includes:
  • the acquisition module 1 is used to acquire the 3D animation to be rendered; the resolution reduction and frame reduction module 2 is used to reduce the resolution and/or frame rate of the 3D animation to be rendered to obtain a low-resolution and/or low-frame-rate 3D animation; the accelerated rendering module 3 is used to start the AI super-resolution and frame-filling function in the renderer.
  • the corresponding AI function is used to start rendering of low-resolution and/or low-frame-rate 3D animations and perform AI accelerated rendering to obtain a 3D animation image sequence after accelerated rendering.
  • an embodiment of the present application provides an electronic device, which includes at least one processor 4, at least one memory 5 and a data bus 6; wherein: the processor 4 and the memory 5 communicate with each other through the data bus 6; the memory 5 stores program instructions that can be executed by the processor 4, and the processor 4 calls the program instructions to execute a three-dimensional animation rendering acceleration method.
  • the processor 4 and the memory 5 communicate with each other through the data bus 6; the memory 5 stores program instructions that can be executed by the processor 4, and the processor 4 calls the program instructions to execute a three-dimensional animation rendering acceleration method.
  • the following is realized:
  • the memory 5 can be but is not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
  • RAM Random Access Memory
  • ROM read-only memory
  • PROM programmable read-only memory
  • EPROM Erasable Programmable Read-Only Memory
  • EEPROM Electrically erasable read-only memory
  • the processor 4 may be an integrated circuit chip with signal processing capability.
  • the processor 4 may be a processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a processor. Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • FIG. 4 is only for illustration, and the electronic device may also include more or fewer components than those shown in Figure 4, or have a different configuration than that shown in Figure 4.
  • Each component shown in Figure 4 may be implemented by hardware, software, or a combination thereof.
  • the present invention provides a computer-readable storage medium on which a computer program is stored.
  • a three-dimensional animation rendering acceleration method is implemented. For example, the following is implemented:
  • each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function.
  • the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings.
  • each box in the block diagram and/or the flowchart, and the combination of boxes in the block diagram and/or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
  • the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Graphics (AREA)
  • Processing Or Creating Images (AREA)
  • Image Generation (AREA)

Abstract

本发明提出了一种三维动画渲染加速方法及系统，涉及动画渲染技术领域。该方法通过降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列，再完成其他后期制作，可以将常规三维动画的渲染时长最大幅度地降低，解决了现有常规三维动画制作流程中因修改而导致的反复渲染需要投入大量精力、费用和浪费大量时间的问题。

Description

一种三维动画渲染加速方法及系统 技术领域
本发明涉及动画渲染技术领域，具体而言，涉及一种三维动画渲染加速方法及系统。
背景技术
随着经济的高速发展，三维动画的需求量和受众对动画的流畅度要求也越来越高。但是整个三维动画的制作过程中难免出现修改的情况，而每次修改都要重新渲染，这样就消耗了大量的时间和金钱在重复渲染的流程上，因此为满足受众的流畅度需求就必须对动画进行加速渲染。
目前三维动画渲染流程中，可以加速渲染的方法包括：1.更换三维渲染器 2.提升电脑配置 3.优化渲染设置 4.与第三方渲染农场合作 5.更换三维软件等。而现有加速渲染的方法需要投入更多费用，根据镜头及场景需求，投入更多的时间精力优化渲染设置，以及更多的学习时间成本。
发明内容
本发明的目的在于提供一种三维动画渲染加速方法及系统，其通过降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画渲染的画面进行AI超分及AI补帧加速渲染，得到加速渲染后的三维动画序列再完成其他后期制作，可以将常规三维动画的渲染时长最大幅度地降低，解决了现有常规三维动画制作流程中因修改 而导致的反复渲染需要投入大量精力、费用和浪费大量时间的问题。
本发明的实施例是这样实现的：
第一方面，本申请实施例提供一种三维动画渲染加速方法，包括以下步骤：获取待渲染的三维动画；降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列。
在本发明的一些实施例中，所述降低待渲染的三维动画的分辨率和帧率的具体步骤包括：在动态动画渲染设置中，将导出序列帧的分辨率降低，得到低分辨率三维动画；在动态动画渲染设置中，将导出序列帧的帧速降低，得到低帧速三维动画。
在本发明的一些实施例中，所述在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染的步骤具体包括：在AI超分工具内，设置超分目标的分辨率，运行后得到AI超分序列帧；所述AI超分工具为预先基于深度学习技术，通过特征提取、特征维度变换、非线性链接、映射、反卷积放大、并经过神经网络处理而得到的；将AI超分序列帧帧导入至AI补帧工具；在AI补帧工具内，设置补帧后的目标帧速，设置完成之后，AI补帧工具基于人工智能算法根据前后帧计算生成中间帧率，根据中间帧率进行补帧，直至补帧完成；将补帧完成后的序列帧导入到后期合成软件中，继续三维动画的后期制作。
在本发明的一些实施例中，还包括还可以对中间帧率无限分隔，以实现任意自定义帧数。
第二方面，本申请实施例提供一种三维动画渲染加速系统，其包括：获取模块，用于获取待渲染的三维动画；降分辨率及降帧模块，用于降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；加速渲染模块：用于在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列。
第三方面，本申请实施例提供一种电子设备，其包括存储器，用于存储一个或多个程序；处理器，当上述一个或多个程序被上述处理器执行时，实现如上述第一方面中任一项上述的方法。
第四方面，本申请实施例提供一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述第一方面中任一项上述的方法。
相对于现有技术，本发明的实施例至少具有如下优点或有益效果：
本发明的实施例提出了一种三维动画渲染加速方法，通过降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染，实现在三维动画渲染的过程中对渲染的画面进行AI超分及AI补帧加速渲染，得到加速渲染后的三维动画序列再完成其他后期制作，可以将常规三维动画的渲染时长最大幅度地降低，解决了现有常规三维动画制作流程中因修改而导致的反复渲染需要投入大量精力、费用和浪费大量时间的问题。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本发明的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1为本发明一种三维动画渲染加速方法一实施例的流程图；
图2为本发明一种三维动画渲染加速方法另一实施例的流程图；
图3为本发明一种三维动画渲染加速系统一实施例的结构框图；
图4为本发明实施例提供的一种电子设备的结构框图。
图标：1、获取模块；2、降分辨率及降帧模块；3、加速渲染模块；4、处理器；5、存储器；6、数据总线。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。
实施例
请参阅图1，本申请实施例提供了一种三维动画渲染加速方法，如图1所示，上述三维动画渲染加速方法包括以下步骤：
步骤S101：获取待渲染的三维动画。
上述步骤中，待渲染的三维动画可以根据用户需求进行三维动画的静态分镜制作以及动态动画的制作而得到。其中，静态分镜制作可以根据用户的动画剧本进行分镜设计，利用三维动画设计软件进行创作得到一帧帧动画图像；然后将得到的动画图像按场景分镜组织到时间轴上进行动态动画的制作。
步骤S102：降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画。
上述步骤中，对降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画。具体可以通过3Dmax、Maya、C4D、Blender等三维软件自带渲染器或第三方渲染器等对待渲染的三维动画进行上述各个渲染参数的动态调整设置，初步得到满足需求的三维动画。当然，也可以预先在3Dmax、Maya、C4D、Blender等三维软件自带的渲染器或第三方渲染器内预置AI超分功能模块和AI补帧功能模块来对三维动画进行AI辅助渲染，提高渲染的效率。
步骤S103：在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列。
上述步骤中，AI超分功能使用了深度学习技术，可通过特征提取，特征维度变换，非线性链接，映射，反卷积放大等过程，并经过神经网络处理，可以让视频在提升分辨率的同时，获得与分辨率同等级的画质，可以让视频在提升分辨率的同时，获得与分辨率同等级的画质。AI补帧功能通过人工智能算法主要根据前后帧计算生成中间帧率，还可以对这个中间帧无限分隔，实现任意自定义帧数
进一步的，在本发明的一些实施例中，所述降低待渲染的三维动画的分辨率和帧率的具体步骤包括：在动态动画渲染设置中，将导出序列帧的分辨率降低，得到低分辨率三维动画；在动态动画渲染设置中，将导出序列帧的帧速降低，得到低帧速三维动画。
示例性的，根据实际需求，在动态动画渲染设置中，将导入序列帧的分辨率及帧速降低至目标分辨率和帧速的50％或更低。
请参阅图2，在本发明的一些实施例中，所述在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染的步骤具体包括：
S201:将低分辨率三维动画的序列帧导入至AI超分工具；
S202:在AI超分工具内，设置超分目标的分辨率，运行后得到AI超分序列帧；所述AI超分工具为预先基于深度学习技术，通过特征提取、特征维度变换、非线性链接、映射、反卷积放大、并经过神经网络处理而得到的；
AI超分功能使用了深度学习技术，可通过特征提取，特征维度变换，非线性链接，映射，反卷积放大等过程，并经过神经网络处理，可以让视频在提升分辨率的同时，获得与目标分辨率同等级的画质，可以让视频在提升分辨率的同时，获得与目标分辨率同等级的画质。
S203:将AI超分序列帧帧导入至AI补帧工具；
S204:在AI补帧工具内，设置补帧后的目标帧速，设置完成之后，AI补帧工具基于人工智能算法根据前后帧计算生成中间帧率，根据中间帧率进行补帧，直至补帧完成；S205:将补帧完成后的序列帧导入到后期合成软 件中，继续三维动画的后期制作。
进一步的，还包括还可以对中间帧率无限分隔，以实现任意自定义帧数。
通过上述AI补帧功能对三维动画进行补帧加速渲染，以目前常见的三维动画帧速来计算(24帧/秒、25帧/秒、30帧/秒、60帧/秒等)，通过上述将渲染的帧速减至12至15帧/秒，大约可缩短50％～80％左右的渲染时间，从而进一步降低常规三维动画的渲染时长。
需要说明的是，可以根据用户渲染三维动画的具体需求，即可以根据原三维动画的分辨率和帧速需求，用户具体可以在渲染器内通过打开AI超分功能、打开AI补帧功能11或同时打开AI超分功能及AI补帧功能实现三维动画的AI加速渲染，可整体缩短70％～90％左右的三维动画的渲染时间，从而将常规三维动画的渲染时长最大幅度地降低，解决了现有常规三维动画制作流程中因修改而导致的反复渲染需要投入大量精力、费用和浪费大量时间的问题，从而达到提升渲染效率的目的。
本发明实施例中未具体展开说明的技术内容，可以通过现有的相关技术实现，属于现有技术，在本发明实施例中不再赘述。
实施例2
相应地，请参阅图3，本申请实施例提供了一种三维动画渲染加速系统，其包括：
获取模块1，用于获取待渲染的三维动画；降分辨率及降帧模块2，用于降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；加速渲染模块3：用于在内置有AI超分和补帧功能的渲染器内启 动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列。
具体的实施方法请参考上述方法实施例1，在此不作过多阐述。
实施例3
请参阅图4，本申请实施例提供了一种电子设备，该电子设备包括至少一个处理器4、至少一个存储器5和数据总线6；其中：处理器4与存储器5通过数据总线6完成相互间的通信；存储器5存储有可被处理器4执行的程序指令，处理器4调用程序指令以执行一种三维动画渲染加速方法。例如实现：
获取待渲染的三维动画；启动渲染器中的AI超分功能和/或AI补帧功能对待渲染的三维动画进行加速渲染，得到加速渲染后的三维动画。
其中，存储器5可以是但不限于，随机存取存储器(Random Access Memory，RAM)，只读存储器(Read Only Memory，ROM)，可编程只读存储器(Programmable Read-Only Memory，PROM)，可擦除只读存储器(Erasable Programmable Read-Only Memory，EPROM)，电可擦除只读存储器(Electric Erasable Programmable Read-Only Memory，EEPROM)等。
处理器4可以是一种集成电路芯片，具有信号处理能力。该处理器4可以是处理器，包括中央处理器(Central Processing Unit，CPU)、网络处理器(Network Processor，NP)等；还可以是数字信号处理器(Digital Signal Processing，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field－Programmable  Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
可以理解，图4所示的结构仅为示意，电子设备还可包括比图4中所示更多或者更少的组件，或者具有与图4所示不同的配置。图4中所示的各组件可以采用硬件、软件或其组合实现。
实施例4
本发明提供一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器4执行时实现一种三维动画渲染加速方法。例如实现：
获取待渲染的三维动画；启动渲染器中的AI超分功能和/或AI补帧功能对待渲染的三维动画进行加速渲染，得到加速渲染后的三维动画。
在本申请所提供的实施例中，应该理解到，所揭露的装置和方法，也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，附图中的流程图和框图显示了根据本申请的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
另外，在本申请各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。
对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其它的具体形式实现本申请。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化囊括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。

Claims (7)

  1. 一种三维动画渲染加速方法，其特征在于，包括：
    获取待渲染的三维动画；
    降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；
    在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列。
  2. 如权利要求1所述的一种三维动画渲染加速方法，其特征在于，所述降低待渲染的三维动画的分辨率和帧率的具体步骤包括：
    在动态动画渲染设置中，将导出序列帧的分辨率降低，得到低分辨率三维动画；
    在动态动画渲染设置中，将导出序列帧的帧速降低，得到低帧速三维动画。
  3. 如权利要求2所述的一种三维动画渲染加速方法，其特征在于，所述在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染的步骤具体包括：
    将低分辨率三维动画的序列帧导入至AI超分工具；
    在AI超分工具内，设置超分目标的分辨率，运行后得到AI超分序列 帧；所述AI超分工具为预先基于深度学习技术，通过特征提取、特征维度变换、非线性链接、映射、反卷积放大、并经过神经网络处理而得到；
    将AI超分序列帧帧导入至AI补帧工具；
    在AI补帧工具内，设置补帧后的目标帧速，设置完成之后，AI补帧工具基于人工智能算法根据前后帧计算生成中间帧率，根据中间帧率进行补帧，直至补帧完成；
    将补帧完成后的序列帧导入到后期合成软件中，继续三维动画的后期制作。
  4. 如权利要求3所述的一种三维动画渲染加速方法，其特征在于，还包括还可以对中间帧率无限分隔，以实现任意自定义帧数。
  5. 一种三维动画渲染加速系统，其特征在于，包括：
    获取模块，用于获取待渲染的三维动画；
    降分辨率及降帧模块，用于降低待渲染的三维动画的分辨率或/和帧率得到低分辨率或/和低帧率三维动画；
    加速渲染模块：用于在内置有AI超分和补帧功能的渲染器内启动对应的AI功能，对低分辨率或/和低帧率三维动画启动渲染并进行AI加速渲染，得到加速渲染后的三维动画图片序列。
  6. 一种电子设备，其特征在于，包括至少一个处理器、至少一个存储器和数据总线；其中：所述处理器与所述存储器通过所述数据总线完成相互间的通信；所述存储器存储有被所述处理器执行的程序指令，所述处理 器调用所述程序指令以执行如权利要求1-4任一项所述的方法。
  7. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该计算机程序被处理器执行时实现如权利要求1-4中任一项所述的方法。
PCT/CN2023/095119 2023-04-12 2023-05-18 一种三维动画渲染加速方法及系统 Ceased WO2024212310A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US18/263,542 US20260105669A1 (en) 2023-04-12 2023-05-18 3d animation rendering acceleration method and system
CA3206104A CA3206104A1 (en) 2023-04-12 2023-05-18 METHOD AND SYSTEM FOR ACCELERATING 3D RENDERING
EP23744350.2A EP4468247A4 (en) 2023-04-12 2023-05-18 Rendering acceleration method and system for three-dimensional animation

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202310382387.0A CN116309982A (zh) 2023-04-12 2023-04-12 一种三维动画渲染加速方法及系统
CN202310382387.0 2023-04-12

Publications (1)

Publication Number Publication Date
WO2024212310A1 true WO2024212310A1 (zh) 2024-10-17

Family

ID=86803301

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/095119 Ceased WO2024212310A1 (zh) 2023-04-12 2023-05-18 一种三维动画渲染加速方法及系统

Country Status (5)

Country Link
US (1) US20260105669A1 (zh)
EP (1) EP4468247A4 (zh)
CN (1) CN116309982A (zh)
CA (1) CA3206104A1 (zh)
WO (1) WO2024212310A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119415206A (zh) * 2024-10-28 2025-02-11 深圳市诺威达电汽有限公司 一种嵌入式设备主页窗口优化系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120580304A (zh) * 2024-03-01 2025-09-02 华为技术有限公司 一种着色方法、电子设备和电子芯片

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130113803A1 (en) * 2009-06-26 2013-05-09 Nvidia Corporation Accelerated rendering with temporally interleaved details
CN111757087A (zh) * 2020-06-30 2020-10-09 北京金山云网络技术有限公司 Vr视频的处理方法、装置和电子设备
CN112492395A (zh) * 2020-11-30 2021-03-12 维沃移动通信有限公司 数据处理方法、装置及电子设备
CN114998087A (zh) * 2021-11-17 2022-09-02 荣耀终端有限公司 渲染方法及装置
CN116012498A (zh) * 2022-12-29 2023-04-25 郭家琪 一种三维动画渲染加速方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220092738A1 (en) * 2020-11-19 2022-03-24 Intel Corporation Methods and apparatus for super-resolution rendering
CN115883853B (zh) * 2021-09-26 2024-04-05 腾讯科技（深圳）有限公司 视频帧播放方法、装置、设备以及存储介质
CN115564644B (zh) * 2022-01-10 2023-07-25 荣耀终端有限公司 图像数据的处理方法、相关设备以及计算机存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130113803A1 (en) * 2009-06-26 2013-05-09 Nvidia Corporation Accelerated rendering with temporally interleaved details
CN111757087A (zh) * 2020-06-30 2020-10-09 北京金山云网络技术有限公司 Vr视频的处理方法、装置和电子设备
CN112492395A (zh) * 2020-11-30 2021-03-12 维沃移动通信有限公司 数据处理方法、装置及电子设备
CN114998087A (zh) * 2021-11-17 2022-09-02 荣耀终端有限公司 渲染方法及装置
CN116012498A (zh) * 2022-12-29 2023-04-25 郭家琪 一种三维动画渲染加速方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4468247A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119415206A (zh) * 2024-10-28 2025-02-11 深圳市诺威达电汽有限公司 一种嵌入式设备主页窗口优化系统

Also Published As

Publication number Publication date
EP4468247A1 (en) 2024-11-27
CA3206104A1 (en) 2025-02-03
EP4468247A4 (en) 2024-11-27
US20260105669A1 (en) 2026-04-16
CN116309982A (zh) 2023-06-23

Similar Documents

Publication Publication Date Title
EP4468247A1 (en) Rendering acceleration method and system for three-dimensional animation
WO2022095742A1 (zh) 图像和视频处理方法及其系统、数据处理设备、介质
CN111586321B (zh) 视频生成方法、装置、电子设备和计算机可读存储介质
CN112669241A (zh) 一种图像处理方法、装置、设备及介质
CN112950515B (zh) 图像处理方法及装置、计算机可读存储介质和电子设备
CN112700516A (zh) 基于深度学习的视频渲染方法、装置、计算机设备以及存储介质
CN114205648B (zh) 插帧方法及装置
CN111462021A (zh) 图像处理方法、装置、电子设备和计算机可读存储介质
WO2026037293A1 (zh) 动画生成方法、装置、电子设备及计算机可读存储介质
CN116012498A (zh) 一种三维动画渲染加速方法及系统
CN115205168A (zh) 图像处理方法、装置、电子设备和存储介质、产品
CN118396861A (zh) 图像增强方法、装置、设备及存储介质
CN114240745B (zh) 一种图像渲染方法、装置、设备及介质
CN110956589A (zh) 一种图像模糊处理方法、装置、设备及存储介质
CN113873254A (zh) 一种光电视频的缩小方法、系统、设备及其存储介质
CN116362958A (zh) 图像处理方法、装置、存储介质及电子设备
CN114972087A (zh) 视频处理方法、装置、设备以及计算机存储介质
CN115617288A (zh) 录屏方法、装置、存储介质及电子设备
CN111179386A (zh) 动画生成方法、装置、设备及存储介质
CN110738615A (zh) 鱼眼图像校正方法、装置、系统及可存储介质
CN119180743B (zh) 分布式渲染处理方法、系统、装置、设备及存储介质
CN111986096A (zh) 基于边缘提取的漫画生成方法及漫画生成装置
CN121792681A (zh) 二维视频处理器、视频处理系统、基于二维视频处理器的视频处理方法和程序产品
CN103474049A (zh) 影像处理装置与影像处理方法
CN116664862A (zh) 图像处理装置及方法

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2023744350

Country of ref document: EP

Effective date: 20230801

NENP Non-entry into the national phase

Ref country code: DE