Adaptive rendering parameter optimization system and method
The adaptive rendering parameter optimization system addresses low efficiency and quality issues by using deep learning to automatically adjust rendering parameters, ensuring efficient and high-quality output.
Patent Information
- Application Number
- CN202411234797.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-12-20
AI Technical Summary
Existing automated rendering tools struggle with complex scenes and diverse rendering requirements, leading to low efficiency and poor quality due to difficulties in automatically adjusting optimal parameters.
An adaptive rendering parameter optimization system utilizing a rendering execution module, data collection module, AI analysis module, and parameter adjustment module, which employs deep learning models to continuously collect and analyze rendering data, identify key factors, and automatically adjust parameters for improved efficiency and quality.
The system achieves efficient and high-quality rendering by continuously adjusting parameters in real-time, reducing manual intervention and enhancing rendering efficiency and quality.
Smart Images
Figure CN119169164A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of computer graphics processing, and in particular to an adaptive rendering parameter optimization system and method. Background Art
[0002] With the continuous development of computer graphics technology, animation rendering plays an increasingly important role in film and television production, game development and other fields. The traditional rendering process requires a lot of manual adjustment and optimization, which not only consumes a lot of manpower and time resources, but also requires extremely high technical skills of artists. Although some existing automated tools can provide a certain degree of help, when faced with complex scenes and diverse rendering requirements, these tools often find it difficult to automatically adjust the optimal rendering parameters, resulting in low rendering efficiency or poor rendering quality. Summary of the invention
[0003] In view of this, an object of the present invention is to provide an adaptive rendering parameter optimization system and method to solve the problem of low rendering efficiency or poor rendering quality in the automatic rendering method in the prior art.
[0004] According to a first aspect of an embodiment of the present invention, there is provided an adaptive rendering parameter optimization system, comprising:
[0005] A rendering execution module, used to execute rendering operations according to rendering parameters and generate rendering results;
[0006] The data collection module is used to continuously collect rendering data during the rendering process;
[0007] An AI analysis module is used to learn and analyze the rendering data using a deep learning model to obtain scene features and rendering requirements, identify key factors affecting rendering efficiency and quality based on the scene features and rendering requirements, and generate improvement suggestion data;
[0008] The parameter adjustment module is used to automatically adjust the rendering parameters in the rendering execution module according to the key factors and the improvement suggestion data.
[0009] Preferably, the rendering execution module is further used to determine whether the rendering result meets a preset rendering target requirement;
[0010] If yes, output the rendering result;
[0011] If not, the rendering result is sent to the AI analysis module, the rendering parameters are adjusted using the AI analysis module and the parameter adjustment module, and the rendering execution module is used to re-execute the rendering operation according to the adjusted rendering parameters.
[0012] Preferably, the rendering data collected by the data collection module includes performance data, image data and physical data;
[0013] The performance data includes at least rendering time and processor load;
[0014] The image data at least includes resolution and sampling rate;
[0015] The physical data includes at least ray tracing depth and reflectivity.
[0016] Preferably, when the data acquisition module acquires rendering data, it records the rendering data of each frame in real time and summarizes the rendering data.
[0017] Preferably, the deep learning model in the AI analysis module includes at least a convolutional neural network and a recurrent neural network;
[0018] The AI analysis module is used to obtain the rendering processing scenario corresponding to the scene features and the rendering requirements, select a deep learning model corresponding to the rendering processing scenario to identify key factors, and generate improvement suggestion data.
[0019] According to a second aspect of an embodiment of the present invention, there is provided an adaptive rendering parameter optimization method, comprising:
[0020] S1. Obtain initial rendering parameters;
[0021] S2, performing rendering operation according to current rendering parameters;
[0022] S3, during the rendering process, continuously collect rendering data;
[0023] S4. Using a deep learning model, learn and analyze the rendering data to obtain scene features and rendering requirements, identify key factors affecting rendering efficiency and quality based on the scene features and rendering requirements, and generate improvement suggestion data;
[0024] S5. Automatically adjust rendering parameters in the rendering execution module according to the key factors and the improvement suggestion data, and repeat step S2 until a rendering result is generated.
[0025] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:
[0026] It is understandable that the adaptive rendering parameter optimization system shown in the present invention uses a rendering execution module to perform rendering operations according to rendering parameters to generate rendering results; the data acquisition module continuously collects rendering data during the rendering process; the AI analysis module uses a deep learning model to learn and analyze the rendering data to obtain scene characteristics and rendering requirements, and identifies key factors affecting rendering efficiency and quality based on the scene characteristics and rendering requirements, and generates improvement suggestion data; the parameter adjustment module automatically adjusts the rendering parameters in the rendering execution module based on the key factors and the improvement suggestion data. It is understandable that the technical solution shown in the present invention can continuously and automatically adjust the rendering parameters during the rendering process, thereby achieving efficient and high-quality rendering output.
[0027] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0029] Figure 1 The figure is a schematic diagram of a workflow of an adaptive rendering parameter optimization system according to an exemplary embodiment. DETAILED DESCRIPTION
[0030] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.
[0031] In one embodiment, an adaptive rendering parameter optimization system is provided, comprising:
[0032] The rendering execution module is used to perform rendering operations according to rendering parameters and generate rendering results.
[0033] The data collection module is used to continuously collect rendering data during the rendering process.
[0034] The AI analysis module is used to use a deep learning model to learn and analyze the rendering data, obtain scene characteristics and rendering requirements, identify key factors affecting rendering efficiency and quality based on the scene characteristics and rendering requirements, and generate improvement suggestion data.
[0035] The parameter adjustment module is used to automatically adjust the rendering parameters in the rendering execution module according to the key factors and the improvement suggestion data.
[0036] Figure 1 is a schematic diagram of a workflow of an adaptive rendering parameter optimization system according to an exemplary embodiment. Figure 1 ,First, the staff configures the scene file with rendering and sets the ,initial rendering parameters, and the rendering execution module performs ,rendering operations according to the initial rendering parameters.
[0037] While the rendering execution module performs rendering operations, the data collection module collects rendering data in real time.
[0038] It should be noted that the rendering data collected by the data acquisition module includes performance data, image data and physical data; the performance data includes at least rendering time and processor load; the image data includes at least resolution and sampling rate; the physical data includes at least ray tracing depth and reflectivity.
[0039] The data acquisition module is responsible for collecting various data in the rendering process. It should be noted that when the data acquisition module collects rendering data, it records the rendering data of each frame in real time and summarizes the rendering data.
[0040] The data collection method of the data collection module can be achieved by inserting special monitoring codes or hardware sensors.
[0041] After the data acquisition module collects various rendering data, the AI analysis module uses a deep learning model to analyze the collected data to understand the scene characteristics and rendering requirements.
[0042] It should be noted that the deep learning model in the AI analysis module includes at least a convolutional neural network and a recurrent neural network.
[0043] The AI analysis module is used to obtain the rendering processing scenario corresponding to the scene features and the rendering requirements, select a deep learning model corresponding to the rendering processing scenario to identify key factors, and generate improvement suggestion data.
[0044] The deep learning models that the AI analysis module can use include at least convolutional neural networks (CNN) and recurrent neural networks (RNN). The AI analysis module can select a suitable deep learning model according to different rendering processing scenarios. For example, in terms of image feature extraction, convolutional neural networks (CNN) have a better performance; in processing time series data, recurrent neural networks (RNN) are more applicable. The AI analysis module can identify key factors that affect rendering efficiency and quality, such as oversampling, unreasonable parameter settings, etc., and generate suggestions for improvement.
[0045] After the AI analysis module generates key factors and improvement suggestion data, the parameter adjustment module automatically adjusts the parameter settings in the rendering engine, such as sampling rate, ray tracing threshold, anti-aliasing strength, etc., based on the output results of the AI analysis module. These parameters directly affect the final rendering effect and performance. Parameter adjustment can use advanced AI algorithms such as reinforcement learning to find the optimal solution through continuous trial and error and feedback.
[0046] It can be understood that the adaptive rendering parameter optimization system shown in this embodiment uses a rendering execution module to perform rendering operations according to rendering parameters to generate rendering results; the data acquisition module continuously collects rendering data during the rendering process; the AI analysis module uses a deep learning model to learn and analyze the rendering data to obtain scene characteristics and rendering requirements, and identifies key factors affecting rendering efficiency and quality based on the scene characteristics and rendering requirements, and generates improvement suggestion data; the parameter adjustment module automatically adjusts the rendering parameters in the rendering execution module based on the key factors and the improvement suggestion data. It can be understood that the technical solution shown in this embodiment can continuously and automatically adjust the rendering parameters during the rendering process, thereby achieving efficient and high-quality rendering output.
[0047] It should be noted that the rendering execution module is also used to determine whether the rendering result meets the preset rendering target requirements; if so, the rendering result is output; if not, the rendering result is sent to the AI analysis module, the rendering parameters are adjusted using the AI analysis module and the parameter adjustment module, and the rendering execution module is used to re-execute the rendering operation according to the adjusted rendering parameters.
[0048] In specific practice, the rendering parameters can be adjusted in real time during the rendering process performed by the rendering execution module. After the rendering execution module generates the rendering result, if the rendering result does not meet the rendering target requirements, the rendering operation can still be re-executed.
[0049] The rendering execution module is not only responsible for the actual graphics rendering, but also needs to monitor the rendering effect and performance in real time to ensure that the expected improvement can be achieved after optimizing the parameters. After the rendering is completed, the rendering execution module will compare the result with the preset target. If there is a deviation, it will continue to iterate and optimize the parameters until the rendering target requirements are met.
[0050] Taking the actual application scenario as an example, in a typical animation film production, the system of this embodiment is used to optimize the rendering parameters. First, the artist sets the initial rendering parameters and starts the rendering task. The rendering execution module performs the rendering operation according to the initial rendering parameters. The data acquisition module begins to collect data during the rendering process and analyzes it through the AI analysis module. The analysis results show that the sampling rate of some scenes is too high, resulting in unnecessary waste of calculations, and the ray tracing depth in some areas is insufficient, affecting the image quality. The parameter adjustment module automatically adjusts the relevant parameters accordingly, and guides the rendering execution module to re-render. After several rounds of iterations, the rendering efficiency was increased by 20%, and the image quality was also significantly improved. Throughout the process, the artist hardly needs to intervene, which greatly reduces the workload.
[0051] It can be understood that the adaptive rendering parameter optimization system provided by this embodiment has the following technical effects:
[0052] Automatic optimization: The system can automatically adjust parameters according to different rendering scenarios and requirements, eliminating the tedious process of manual parameter adjustment.
[0053] Real-time feedback: By monitoring rendering effects and performance in real time, the system can respond quickly and adjust strategies to ensure rendering quality.
[0054] Continuous learning: The system has the ability to self-learn and adapt. With the accumulation of usage time, the rendering efficiency and quality will continue to improve.
[0055] Strong versatility: The system is not only suitable for traditional offline rendering, but also for real-time rendering and game engines, and has broad application prospects.
[0056] According to a second aspect of an embodiment of the present invention, there is provided an adaptive rendering parameter optimization method, comprising:
[0057] S1. Obtain initial rendering parameters;
[0058] S2, performing rendering operation according to current rendering parameters;
[0059] S3, during the rendering process, continuously collect rendering data;
[0060] S4. Using a deep learning model, learn and analyze the rendering data to obtain scene features and rendering requirements, and identify key factors affecting rendering efficiency and quality based on the scene features and rendering requirements;
[0061] S5. Automatically adjust rendering parameters in the rendering execution module according to the key factors, and repeat step S2 until a rendering result is generated.
[0062] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.
[0063] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.
[0064] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.
[0065] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0066] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0067] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0068] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.
[0069] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0070] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. An adaptive rendering parameter optimization system, characterized in that: include: A rendering execution module, used to execute rendering operations according to rendering parameters and generate rendering results; The data collection module is used to continuously collect rendering data during the rendering process; An AI analysis module is used to learn and analyze the rendering data using a deep learning model to obtain scene features and rendering requirements, identify key factors affecting rendering efficiency and quality based on the scene features and rendering requirements, and generate improvement suggestion data; The parameter adjustment module is used to automatically adjust the rendering parameters in the rendering execution module according to the key factors and the improvement suggestion data.
2. The adaptive rendering parameter optimization system according to claim 1, characterized in that: The rendering execution module is also used to determine whether the rendering result meets the preset rendering target requirement; If yes, output the rendering result; If not, the rendering result is sent to the AI analysis module, the rendering parameters are adjusted using the AI analysis module and the parameter adjustment module, and the rendering execution module is used to re-execute the rendering operation according to the adjusted rendering parameters.
3. The adaptive rendering parameter optimization system according to claim 1, characterized in that: The data acquisition module acquires rendering data including performance data, image data and physical data; The performance data includes at least rendering time and processor load; The image data at least includes resolution and sampling rate; The physical data includes at least ray tracing depth and reflectivity.
4. The adaptive rendering parameter optimization system according to claim 3, characterized in that: When the data acquisition module acquires rendering data, it records the rendering data of each frame in real time and summarizes the rendering data.
5. The adaptive rendering parameter optimization system according to claim 1, characterized in that: The deep learning model in the AI analysis module includes at least a convolutional neural network and a recurrent neural network; The AI analysis module is used to obtain the rendering processing scenario corresponding to the scene features and the rendering requirements, select a deep learning model corresponding to the rendering processing scenario to identify key factors, and generate improvement suggestion data.
6. An adaptive rendering parameter optimization method, characterized in that: include: S1. Obtain initial rendering parameters; S2, performing rendering operation according to current rendering parameters; S3, during the rendering process, continuously collect rendering data; S4. Using a deep learning model, learn and analyze the rendering data to obtain scene features and rendering requirements, identify key factors affecting rendering efficiency and quality based on the scene features and rendering requirements, and generate improvement suggestion data; S5. Automatically adjust rendering parameters in the rendering execution module according to the key factors and the improvement suggestion data, and repeat step S2 until a rendering result is generated.