An expression action control method and device for three-dimensional cartoon production

Abstract

The application provides a kind of expression action control method and device for three-dimensional cartoon production, comprising: step S1, obtaining the description vocabulary of the current to-be-produced character of the to-be-produced three-dimensional cartoon;Step S2, obtain the historical wind evaluation related to the description vocabulary consistent with the cartoon character and the facial expression of the cartoon character, filter out the top N cartoon characters of historical wind evaluation as positive reference characters, N is a positive integer;Step S3, obtain the basic face model of the current to-be-produced character, respectively migrate the facial expression action of all positive reference characters to the basic face model of the current to-be-produced character, obtain and control the facial expression action of the current to-be-produced character is generated.The facial expression action of the application is good by migrating the facial expression action of the historical wind evaluation of the cartoon character to the basic face model of the current to-be-produced character, thereby improving the facial expression action of the three-dimensional cartoon production.

Description

Technical Field

[0001] The present invention relates to the technical field of animation production, and in particular to a method and device for controlling facial expressions and movements in three-dimensional animation production. Background Art

[0002] In the production of 3D animation, the control of facial expressions is crucial. Whether the facial expressions are smooth and vivid, whether they are consistent with the character's personality, etc. will affect the recognition of a 3D animation.

[0003] In existing 3D animation production, facial expressions are typically simulated by technicians, or captured from real human faces to create anime-style expressions. In both cases, the resulting characters have mixed reviews. 3D animation is expensive to produce, and if a single detail like a character's facial expression affects the overall quality of the production, the result is not worth the effort.

[0004] Therefore, it is necessary to provide a production method that can improve the reputation of facial expression and action. Summary of the Invention

[0005] In order to solve the above problems in the prior art, the present invention provides a method and device for controlling facial expressions and movements produced in three-dimensional animation, so as to improve the reputation of facial expressions and movements produced in three-dimensional animation.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] In a first aspect, the present invention provides a method for controlling facial expressions in three-dimensional animation production, comprising:

[0008] Step S1, obtaining a descriptive vocabulary of a current character to be produced in a 3D animation to be produced;

[0009] Step S2: Obtain historical reputations of anime characters that are consistent with the descriptive words and related to the facial expressions of the anime characters, and select the top N anime characters with the highest historical reputations as positive reference characters, where N is a positive integer;

[0010] Step S3: obtaining the basic facial model of the character to be produced, migrating the facial expressions and movements of all the front reference characters to the basic facial model of the character to be produced, and obtaining and controlling the generation of the facial expressions and movements of the character to be produced.

[0011] The beneficial effect of the present invention is that by obtaining other cartoon characters with the same descriptive vocabulary as the current character to be produced, and screening out cartoon characters with good reputation based on historical reputation, their facial expressions and movements are transferred to the basic facial model of the current character to be produced, thereby improving the reputation of the facial expressions and movements produced by the three-dimensional cartoon.

[0012] Optionally, the step S3 comprises:

[0013] obtaining a basic face model of the current character to be made;

[0014] extracting all facial two-dimensional feature points of the positive reference characters based on the DDE model for regression, and then mapping to the current character to be made to obtain and control the facial expression action of the current character to be made.

[0015] According to the above description, the facial two-dimensional feature points of all positive reference characters are extracted based on the DDE model for regression, and then mapped to the current character to be made, without the need for prior tagging operation, thereby improving the processing speed.

[0016] Optionally, the obtaining and controlling the facial expression action of the current character to be made in the step S3 comprises:

[0017] controlling to generate and display the reference facial expression action obtained by each of the positive reference characters, and selecting the reference facial expression action selected by the user as the facial expression action of the current character to be made.

[0018] According to the above description, all generated reference facial expression actions are provided for the technical personnel to select, which firstly ensures the market reputation of the facial expression action made by the three-dimensional animation, secondly can avoid the deviation of part of the facial expression action in the migration process, and finally the technical personnel can also select according to the overall style of the three-dimensional animation to be made by the company, so as to take into account the market reputation, result accuracy and company requirements.

[0019] Optionally, the description vocabulary comprises gender, animation style, character personality and facial expression to be generated.

[0020] According to the above description, the limitation of the description vocabulary is helpful to obtain suitable reference facial expression action.

[0021] Optionally, the obtaining of the animation characters consistent with the description vocabulary and the historical reputation related to the facial expression of the animation characters is obtained through a network crawler.

[0022] In a second aspect, the present application provides an expression action control device for three-dimensional animation production, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to realize the following:

[0023] Step S1, obtaining the description vocabulary of the current character to be made of the three-dimensional animation to be made;

[0024] Step S2, obtaining an animation character consistent with the description vocabulary and a historical evaluation related to the facial expression of the animation character, screening out the top N animation characters of the historical evaluation as positive reference characters, and the N is a positive integer;

[0025] Step S3, obtaining a basic face model of the current to-be-made character, migrating the facial expression actions of all positive reference characters to the basic face model of the current to-be-made character respectively, and obtaining and controlling generation of the facial expression action of the current to-be-made character.

[0026] Optionally, the step S3 comprises:

[0027] obtaining a basic face model of the current to-be-made character;

[0028] extracting the two-dimensional feature points of the face of all positive reference characters based on the DDE model for regression, and then mapping to the current to-be-made character to obtain and control generation of the facial expression action of the current to-be-made character.

[0029] Optionally, the obtaining and controlling generation of the facial expression action of the current to-be-made character in the step S3 comprises:

[0030] controlling generation and display of the reference facial expression action obtained by each of the positive reference characters, and selecting the reference facial expression action selected by the user as the facial expression action of the current to-be-made character.

[0031] Optionally, the description vocabulary comprises gender, animation style, character personality and the current to-be-generated facial expression.

[0032] Optionally, the obtaining of the animation character consistent with the description vocabulary and the historical evaluation related to the facial expression of the animation character is obtained through a network crawler.

[0033] The technical effect corresponding to the three-dimensional animation production expression action control device provided in the second aspect is referred to the related description of the three-dimensional animation production expression action control method provided in the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 The main flowchart of the three-dimensional animation production expression action control method of the embodiment of the application;

[0035] Figure 2 The structure diagram of the three-dimensional animation production expression action control device of the embodiment of the application.

[0036]

Explanation of reference numerals

[0037] 1. An expression action control device for three-dimensional cartoon production;

[0038] 2. A processor;

[0039] 3. A memory. DETAILED DESCRIPTION

[0040] In order to better understand the above technical solutions, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present application can be more clearly, thoroughly and completely understood, and so that the scope of the present application can be accurately conveyed to those skilled in the art.

[0041] Embodiment One

[0042] Referring to Figure 1 An expression action control method for three-dimensional cartoon production, comprising:

[0043] Step S1, obtaining a description vocabulary of a current character to be produced for three-dimensional cartoon production;

[0044] The description vocabulary includes gender, cartoon style, character personality, and current facial expression to be generated. In this embodiment, for example, the description vocabulary of the current character to be produced is female, sports, cute, and smile; the description vocabulary of the current character to be produced is male, hot-blooded, and a character with a big head, and so on. In order to obtain a high degree of relevance for the subsequent cartoon character, the cartoon style, character personality, and current facial expression to be generated are not limited to using only one word, for example, the character personality is cute and natural.

[0045] Step S2, obtaining a cartoon character consistent with the description vocabulary and a historical evaluation related to the facial expression of the cartoon character, and screening the top N cartoon characters in the historical evaluation as positive reference characters, N being a positive integer;

[0046] The historical evaluation of the cartoon character consistent with the description vocabulary and related to the facial expression of the cartoon character is obtained through a web crawler.

[0047] In this embodiment, N is 10, that is, the top 10 cartoon characters in the historical evaluation are obtained as positive reference characters. In other embodiments, N can be 5, 8, 12, 20, etc.

[0048] Step S3, obtaining a basic facial model of the current character to be produced, migrating the facial expression actions of all positive reference characters to the basic facial model of the current character to be produced, and obtaining and controlling the generation of the facial expression action of the current character to be produced.

[0049] In the embodiment, step S3 comprises:

[0050] obtaining a basic face model of the current character to be made;

[0051] extracting all the two-dimensional feature points of the face of the positive reference character based on the DDE model, and then mapping to the current character to be made;

[0052] controlling to generate and display the reference facial expression action of each positive reference character, and selecting the reference facial expression action selected by the user as the facial expression action of the current character to be made.

[0053] Wherein, DDE is Displaced Dynamic Expression, which means that the model can realize the migration of facial expression from two-dimensional image to three-dimensional animation model without prior tagging operation, thereby saving a lot of tagging time and improving processing speed.

[0054] Wherein, according to step S3, the reference facial expression action of the 10 positive reference characters can be obtained, and the technical personnel can select one of the reference facial expression actions as the facial expression action of the current character to be made according to their own needs. Therefore, because the selection range of the 10 positive reference characters is relatively high, and the technical personnel's secondary screening can greatly guarantee the market reputation of the facial expression action made by the three-dimensional animation. Secondly, since the embodiment is matched with the corresponding character through the network crawler, there is a possibility that the facial expression of the character is not adapted to the current character to be made, therefore, compared with directly using the reference facial expression action of the positive reference character with the best reputation, it can also avoid part of the problem. Finally, the network crawler obtains data according to the description vocabulary, based on the accuracy of the description vocabulary and the accuracy of the data obtained by the crawler, the technical personnel can also meet their own requirements for the three-dimensional animation through secondary screening, so as to balance the market reputation, the accuracy of the result and the company's requirements.

[0055] Embodiment two

[0056] Please refer to Figure 2 A three-dimensional animation expression action control device 1, comprising a memory 3, a processor 2 and a computer program stored in the memory 3 and executable on the processor 2, wherein the processor 2 executes the computer program to realize the steps in the above embodiment one.

[0057] The system / device used for implementing the method of the embodiments of the present application described above can be understood by those skilled in the art based on the method of the embodiments of the present application described above, and thus will not be described here again. The system / device used for implementing the method of the embodiments of the present application described above all belong to the scope of the present application.

[0058] Those skilled in the art will appreciate that embodiments of the present application can be supplied as a method, a system or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage media, etc.) containing computer-usable program code.

[0059] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as a combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions.

[0060] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims, the word "first", "second", "third" etc. does not limit the number for these elements. These words are only used to distinguish between alternative claims. The word "comprise", "comprising", "contain", "containing" or "including" does not exclude the presence of elements or steps not listed in a claim. The word "one" does not exclude the presence of plural referents or steps.

[0061] In addition, it should be noted that in the description of the specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. 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 application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0062] While the preferred embodiments of the application have been described, those skilled in the art will recognize that many modifications and variations of this preferred embodiment are possible without departing from the spirit or scope of the present application. Thus, it is intended that the present application encompass all such modifications and variations as fall within the scope of the appended claims and their equivalents.

[0063] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for controlling facial expressions in three-dimensional animation production, characterized in that: include: Step S1, obtaining a descriptive vocabulary of a current character to be produced in a 3D animation to be produced; Step S2: Obtain historical reputations of anime characters that are consistent with the descriptive words and related to the facial expressions of the anime characters, and select the top N anime characters with the highest historical reputations as positive reference characters, where N is a positive integer; Step S3, obtaining a basic facial model of the character to be produced, migrating the facial expressions of all the front reference characters to the basic facial model of the character to be produced, and obtaining and controlling the generation of the facial expressions of the character to be produced; The step S3 of obtaining and controlling the generation of the facial expression of the character to be produced includes: Control the generation and display of the reference facial expression movements obtained for each of the front reference characters, and use the reference facial expression movements selected by the user as the facial expression movements of the character to be currently produced.

2. The facial expression control method for 3D animation production according to claim 1, characterized in that: The step S3 comprises: Obtaining a basic facial model of the character to be produced; Based on the DDE model, the facial two-dimensional feature points of all front reference characters are extracted and regressed, and then mapped to the current character to be produced, so as to obtain and control the generation of facial expression movements of the current character to be produced.

3. The facial expression control method for 3D animation production according to claim 1, characterized in that: The description vocabulary includes gender, animation style, character personality and facial expressions that need to be generated currently.

4. The facial expression control method for three-dimensional animation production according to any one of claims 1 to 3, characterized in that: The obtained animation characters consistent with the description words and the historical reputation related to the facial expressions of the animation characters are obtained by web crawlers.

5. A facial expression control device for three-dimensional animation production, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the following is achieved: Step S1, obtaining a descriptive vocabulary of a current character to be produced in a 3D animation to be produced; Step S2: Obtain historical reputations of anime characters that are consistent with the descriptive words and related to the facial expressions of the anime characters, and select the top N anime characters with the highest historical reputations as positive reference characters, where N is a positive integer; Step S3, obtaining a basic facial model of the character to be produced, migrating the facial expressions of all the front reference characters to the basic facial model of the character to be produced, and obtaining and controlling the generation of the facial expressions of the character to be produced; The step S3 of obtaining and controlling the generation of the facial expression of the character to be produced includes: Control the generation and display of the reference facial expression movements obtained for each of the front reference characters, and use the reference facial expression movements selected by the user as the facial expression movements of the character to be currently produced.

6. The facial expression control device for three-dimensional animation production according to claim 5, characterized in that: The step S3 comprises: Obtaining a basic facial model of the character to be produced; Based on the DDE model, the facial two-dimensional feature points of all front reference characters are extracted and regressed, and then mapped to the current character to be produced, so as to obtain and control the generation of facial expression movements of the current character to be produced.

7. The facial expression control device for three-dimensional animation production according to claim 5, characterized in that: The description vocabulary includes gender, animation style, character personality and facial expressions that need to be generated currently.

8. The facial expression control device for three-dimensional animation production according to any one of claims 5 to 7, characterized in that: The obtained animation characters consistent with the description words and the historical reputation related to the facial expressions of the animation characters are obtained by web crawlers.

Images