Personalized customization drawing system and method

Abstract

The invention provides a personalized customization drawing system and method, and the system comprises a modeling module which is used for carrying out the three-dimensional modeling of a garment and a model, so as to generate a three-dimensional model, a rendering module which is used for rendering the three-dimensional model, so as to obtain a rendered picture, a garment element and model element analysis module which is used for analyzing the rendered picture, and a drawing module which is used for drawing the rendered picture. And the modification module is used for modifying the rendered picture by adjusting the clothing elements and the model elements and / or adding new elements so as to obtain a finished picture. According to the scheme provided by the invention, the quick drawing of the clothing picture can be realized with high quality, the drawing and content distribution efficiency and marketing requirements are improved, the high fidelity of the modeled clothing can be kept, the operation difficulty is low, the time cost and the labor cost are remarkably reduced, and meanwhile, the method also has a relatively wide application range.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional modeling, and in particular relates to a personalized customized drawing system and method. Background Art

[0002] With the popularity of online shopping and the increase in personalized consumption demand, people have put forward higher requirements for personalized customization of clothing. Traditional clothing customization methods mainly rely on graphic design and fitting, which cannot intuitively show the effect of clothing on models, and it is difficult to intuitively display the actual effect of clothing on different human bodies.

[0003] At the same time, in the field of clothing customization and design, it is of great significance to provide customers with personalized clothing effect displays. Users often hope to be able to adjust clothing styles, colors, accessories, etc. according to their own needs and preferences, and be able to preview the finished product effects through various elements of the model.

[0004] There are already some methods for customizing images in the existing technology, such as manual drawing, image editing software, or virtual reality technology. However, these methods still have some limitations and shortcomings, such as lack of realism and accuracy.

[0005] In addition, customized images require a lot of manpower and time, and using image editing software to produce images requires users to have certain image processing skills. Virtual reality technology requires less expensive equipment and expertise, and is more complicated to operate for ordinary users. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present disclosure proposes a personalized customized image output system, the system comprising:

[0007] A modeling module, used for three-dimensional modeling of clothing and models to generate a three-dimensional model;

[0008] A rendering module, used for rendering the three-dimensional model to obtain a rendered image;

[0009] A parsing module, used for parsing clothing elements and model elements of the rendered image;

[0010] The modification module is used to modify the rendered image by adjusting the clothing elements, the model elements and / or adding new elements to obtain a finished image.

[0011] Specifically, the modeling module includes:

[0012] A clothing modeling unit, used for performing three-dimensional modeling on the clothing to construct a three-dimensional clothing model;

[0013] A model modeling unit is used to provide the user with the option of customizing a digital model, and based on the three-dimensional clothing model and the customized digital model, perform clothing simulation in the modeling software to generate the three-dimensional model; or to provide the user with a plurality of mannequins for the user to choose from, and simulate the three-dimensional clothing model and the mannequin selected by the user to a stable state through a simulation engine of the modeling software to generate the three-dimensional model.

[0014] Optionally, the modeling module further includes a scene modeling unit, and the scene modeling unit is used to preset a scene suitable for the clothing and the model when generating the three-dimensional model, so as to generate the three-dimensional model including the scene;

[0015] The parsing module comprises:

[0016] A clothing parsing unit, used for parsing clothing elements of the rendered image;

[0017] A model parsing unit, used for parsing model elements of the rendered image;

[0018] A scene parsing unit is used to parse the scene elements of the rendered image.

[0019] Preferably, the modification module includes:

[0020] An encoder, used for encoding the rendered image;

[0021] An adjustment unit, used for modifying the encoded rendering image by adjusting the clothing elements, the model elements and / or adding new elements to obtain a modified image;

[0022] A decoder is used to decode the modified image to obtain the finished image.

[0023] The present disclosure also proposes a personalized customized drawing method, the method comprising:

[0024] Performing three-dimensional modeling on the clothing and the model to generate a three-dimensional model, and rendering the three-dimensional model to obtain a rendered image;

[0025] Analyzing clothing elements and model elements of the rendered image;

[0026] The rendered image is modified by adjusting the clothing elements, the model elements and / or adding new elements to obtain a finished image.

[0027] Optionally, the method further comprises:

[0028] When generating the three-dimensional model, presetting a scene suitable for the clothing and the model to generate the three-dimensional model including the scene;

[0029] When parsing the clothing elements and model elements of the rendered image, the scene elements of the rendered image are also parsed, so that the rendered image can be modified by adjusting the scene elements.

[0030] Preferably, the modifying the rendered image by adjusting the clothing elements, the model elements and / or adding new elements to obtain a finished image comprises:

[0031] Encoding the rendered image;

[0032] Modifying the encoded rendering image by adjusting the clothing element, the model element and / or adding a new element to obtain a modified image;

[0033] The modified picture is decoded to obtain the finished picture.

[0034] Specifically, the modifying the rendered image by adding new elements includes:

[0035] Adding scene elements to modify the scene of the rendered image based on the scene elements;

[0036] and / or, adding character elements to modify the model based on the character elements;

[0037] And / or, adding text information so that the text information is displayed on the rendered image.

[0038] Specifically, the model elements include the model's skin color, expression, movement, face shape, hairstyle, figure and / or makeup;

[0039] The clothing elements include the silhouette, texture, color and / or style of the clothing.

[0040] Optionally, performing three-dimensional modeling on the clothing and the model to generate a three-dimensional model includes:

[0041] Performing three-dimensional modeling on the garment to construct a three-dimensional garment model;

[0042] Providing the user with the option of customizing a digital model, and based on the three-dimensional clothing model and the customized digital model, performing clothing simulation in the modeling software to generate the three-dimensional model; or providing the user with a plurality of mannequins for the user to choose from, simulating the three-dimensional clothing model and the mannequin selected by the user to a stable state through a simulation engine of the modeling software to generate the three-dimensional model.

[0043] The present disclosure also proposes another personalized customized drawing method, the method comprising:

[0044] Obtaining a rendered image; the rendered image at least includes a model element and a clothing element;

[0045] parsing the clothing elements and the model elements in the rendered image;

[0046] At least one adjustment instruction for the clothing element and the model element is received, and the rendered image is modified to obtain a finished image.

[0047] Optionally, the “obtaining a rendered image” includes:

[0048] Performing three-dimensional modeling on clothing and models to generate a three-dimensional model, and rendering the three-dimensional model to obtain a rendered image;

[0049] Or, receive rendered images imported by users.

[0050] Specifically, the “analyzing clothing elements and model elements in the rendered image” includes:

[0051] The clothing elements and the model elements in the rendered image are analyzed by using a preset designated and / or image analysis algorithm.

[0052] Preferably, the method further comprises:

[0053] Displaying an element editing interface; the element editing interface includes at least one editing area of ​​the clothing element and the model element;

[0054] Receive the user's input in the editing area and confirm the adjustment instruction.

[0055] Or, displaying an element editing interface; the element editing interface includes an element detail option and an attribute option;

[0056] Receive user selection input for element detail options and / or attribute options, and confirm the adjustment instruction.

[0057] Furthermore, the “receiving at least one adjustment instruction for the clothing element and the model element, and modifying the rendered image to obtain a finished image” includes:

[0058] Encoding the rendered image to obtain an initial feature tensor of the rendered image;

[0059] Based on the received adjustment instruction, modify some eigenvalues ​​in the initial feature tensor to form a target feature tensor;

[0060] The target feature tensor is decoded to obtain the finished image.

[0061] Furthermore, the preset designation mode is implemented based on a configuration modeling tag, and the method further includes:

[0062] If the method of parsing the clothing elements and the model elements in the rendered image includes preset designation, the element detail options correspond to the modeling tags.

[0063] The present disclosure also provides an electronic device, comprising:

[0064] processor;

[0065] a memory for storing processor-executable instructions;

[0066] The processor implements the method described above by running the executable instructions.

[0067] The present disclosure also proposes a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described above are implemented.

[0068] The present disclosure has at least the following beneficial effects:

[0069] The solution proposed in this disclosure provides users with the ability to customize the system. The system has the function of analyzing multiple elements, so that users can obtain more realistic and lifelike pictures according to their needs and preferences. Users can customize the rendered pictures by adjusting clothing elements, model elements, or adding new elements to accurately present the effect of clothing on the model;

[0070] Furthermore, this solution can achieve the presentation effect of clothing on different models, such as hairstyle, face shape, expression, posture, etc., to show the effect of clothing more vividly and realistically; at the same time, the presentation scene of clothing can be customized, such as beach, street shooting, show, etc., which is more helpful to enhance the different concerns of different groups on clothing performance;

[0071] Preferably, this solution can be applied to the rapid customization of graphics on online e-commerce platforms. By rapidly producing graphics from digital modeling to e-commerce scenarios, the digital modeling capabilities can be fully utilized without the need for highly complex modeling of models. At the same time, there is no need to go through traditional operations such as sample clothing, model shooting, and photo editing. Rapid e-commerce graphics and content distribution can be achieved with one click.

[0072] Therefore, the present disclosure provides a personalized customized drawing system and method. The solution proposed in the present disclosure can realize the rapid drawing of clothing pictures with high quality, improve the efficiency of drawing and content distribution and marketing needs, maintain the high fidelity of modeled clothing, and has low operating difficulty, which significantly reduces time and labor costs, and also has a wider range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 A schematic diagram of the overall module structure of the personalized customized image output system provided in Example 1;

[0075] Figure 2 A schematic diagram of the overall process of the personalized customized drawing method provided in Example 2;

[0076] Figure 3 A schematic diagram of the process of generating a three-dimensional model;

[0077] Figure 4 A schematic diagram of the process to obtain the finished product picture;

[0078] Figure 5 A schematic diagram of the overall process of another personalized customized drawing method provided in Example 2;

[0079] Figure 6 A flowchart of a method for modifying a rendered image to obtain a finished image;

[0080] Figure 7 This is an example diagram of the module structure of an electronic device.

[0081] Reference numerals

[0082] 1-modeling module; 2-rendering module; 3-parsing module; 4-modification module; 11-clothing modeling unit; 12-model modeling unit; 13-scene modeling unit; 31-clothing parsing unit; 32-model parsing unit; 33-scene parsing unit; 41-encoder; 42-adjustment unit; 43-decoder; 401-processor; 402-internal bus; 403-network interface; 404-memory; 405-non-volatile memory. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0084] In the following, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0085] Hereinafter, the terms "include" or "may include" used in various embodiments of the present disclosure indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "include", "have", and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or a combination of the foregoing, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components, or a combination of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or a combination of the foregoing.

[0086] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0087] The expressions (such as "first", "second", etc.) used in the various embodiments of the present disclosure may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0088] It should be noted that in the present disclosure, unless otherwise clearly specified and defined, the terms such as "installation", "connection", "fixation" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal communication of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present disclosure can be understood according to the specific circumstances.

[0089] In the present disclosure, a person of ordinary skill in the art needs to understand that the terms indicating orientation or positional relationships herein are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present disclosure.

[0090] The terms used in the various embodiments of the present disclosure are only used for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the meanings commonly understood by ordinary technicians in the field to which the various embodiments of the present disclosure belong. The terms (such as the terms defined in the generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.

[0091] Example 1

[0092] This embodiment proposes a personalized customized image output system, which can realize the rapid output of three-dimensional clothing models with high quality. It can realize efficient single image and group image output of any scene, model, posture, and perspective, improve content distribution efficiency and marketing needs, while maintaining high fidelity of modeled clothing, see Figure 1 , the system comprising:

[0093] Modeling module 1, used for performing three-dimensional modeling of clothing and models to generate a three-dimensional model;

[0094] Rendering module 2, used for rendering the three-dimensional model to obtain a rendered image;

[0095] Parsing module 3, used to parse clothing elements and model elements of the rendered image;

[0096] The modification module 4 is used to modify the rendered image by adjusting clothing elements, model elements and / or adding new elements to obtain a finished image.

[0097] In this embodiment, the rendering module 2 is used to render the clothing in the three-dimensional model to make the clothing more realistic. The model elements analyzed by the analysis module 3 and used for adjustment by the modification module 4 include the model's skin color, expression, action, face shape, hairstyle, figure and / or makeup; clothing elements include the outline, texture, color and / or style of the clothing;

[0098] Modification module 4 also supports the prior information parsed by parsing module 3 from clothing, models, etc., and uses this prior information as controllable and stably generated advance knowledge of generative AI, effectively ensuring the robustness of the system operation.

[0099] It should be noted that the pictures obtained by the personalized customized image output system proposed in this embodiment can be a single picture or a set of multiple pictures, which fully utilizes the digital modeling capabilities and does not require highly complex model modeling. At the same time, there is no need to go through traditional sample clothing, model shooting, photo editing and other operations, thereby achieving rapid image output and content distribution.

[0100] When the user needs to obtain a set of multiple groups of pictures, the clothing elements, model elements and newly added elements can be adjusted accordingly, so that some of the elements are the same, while other elements can be changed according to the user's needs, and finally the group of pictures required by the user is generated.

[0101] For example, the models in the generated set of pictures may be fixed as the same by making some of the model elements the same, while changing other model elements so that the models have different expressions, movements, and postures;

[0102] The clothes in the generated set of pictures can be fixed to the same style by making some clothing elements the same, while changing other clothing elements to make the clothes have different colors and textures;

[0103] The clothing in the generated group of pictures can be fixed to the same background by keeping a part of the scene elements the same, while changing another part of the scene elements so that the scene has different perspectives.

[0104] In this embodiment, the modeling module 1 completes the three-dimensional modeling of clothing and models in the clothing modeling unit 11, firstly performs 3D clothing modeling, and after completing clothing modeling, the user can select digital model or mannequin modeling to generate a three-dimensional model. Specifically, the modeling module 1 includes:

[0105] A clothing modeling unit 11 is used to perform three-dimensional modeling on clothing to construct a three-dimensional clothing model;

[0106] The model modeling unit 12 is used to provide users with the option of customizing digital models, and based on the three-dimensional clothing model and the customized digital model, perform clothing simulation in the modeling software to generate a three-dimensional model; or to provide users with multiple mannequins for users to choose from, and simulate the three-dimensional clothing model and the mannequin selected by the user to a stable state through the simulation engine of the modeling software to generate a three-dimensional model.

[0107] Optionally, the modeling module 1 can also model the scene while modeling the clothing and the model, and can also add scene elements through the modification module 4 to automatically generate a picture scene. When the modeling module 1 models the scene while modeling the clothing and the model, the modeling module 1 also includes:

[0108] The scene modeling unit 13 is used to preset a scene suitable for the clothing and the model when generating a three-dimensional model, so as to generate a three-dimensional model including the scene.

[0109] Accordingly, the parsing module 3 includes:

[0110] A clothing parsing unit 31, for parsing clothing elements of a rendered image;

[0111] A model parsing unit 32, for parsing model elements of the rendered image;

[0112] The scene parsing unit 33 is used to parse the scene elements of the rendered image.

[0113] In this way, the presentation effects of clothing on different models can be achieved, such as hairstyle, face shape, expression, posture, etc., which can show the effect of clothing more vividly and realistically; at the same time, the presentation scenes of clothing can be customized, such as beaches, street shots, catwalks, etc., which is more helpful to enhance the different concerns of different groups on clothing performance.

[0114] Specifically, modification module 4 includes:

[0115] Encoder 41, used to encode the rendered image;

[0116] An adjustment unit 42, used to modify the encoded rendering image by adjusting clothing elements, model elements and / or adding new elements to obtain a modified image;

[0117] The decoder 43 is used to decode the modified picture to obtain a finished picture.

[0118] It should be noted that the encoder 41 can convert network calculations from image pixel space to latent space, achieve data dimensionality reduction and compression, and reduce the amount of calculation. This can improve the quality of model generation, better control the input conditions of the adjustment unit 42, and can be applied to some occasions that require special viewing angles, thereby better meeting design requirements and improving efficiency.

[0119] Specifically, the elements added by the adjustment unit 42 may include but are not limited to:

[0120] Scene elements, so that the adjustment unit 42 can modify the scene of the rendered image based on the scene elements, and the scene elements include but are not limited to the color tone, layout, matching and other elements of the scene;

[0121] Character elements, so that the adjustment unit 42 can modify the model based on the character elements, including but not limited to the model's age, gender, action, etc.;

[0122] Text information, so that the adjustment unit 42 can display the text information on the rendered image, the text information can include clothing prices, current hot items, fashion trends, current hot topics and other information closely related to business, so that the personalized customized image output system proposed in this embodiment can be applied to the rapid customized image output of the online e-commerce platform;

[0123] By quickly producing images from digital modeling to e-commerce scenarios, we can fully utilize the digital modeling capabilities without the need for highly complex modeling. At the same time, there is no need to go through traditional operations such as sampling, model shooting, and photo editing. We can achieve rapid e-commerce image production and rapid content distribution with one click.

[0124] In this embodiment, the adjustment unit 42 includes a generation network. It should be noted that the generation network is a machine model with a learning function. The generation network can extract rules and patterns from existing data through learning based on probability models and statistical methods, and use these patterns to generate new data, such as generating new samples of images, texts, audio or other data.

[0125] Example 2

[0126] This embodiment proposes a personalized customized drawing method, please refer to Figure 2 , the method comprising:

[0127] S210: Perform three-dimensional modeling on the clothing and the model to generate a three-dimensional model, and render the three-dimensional model to obtain a rendered image.

[0128] Specifically, the rendering of the three-dimensional model in S210 is specifically rendering the clothes in the three-dimensional model to make the clothes more realistic.

[0129] The system of the present disclosure also supports another method of obtaining rendered images. There may be multiple methods of obtaining rendered images, such as providing an interactive interface through which users can import rendered images into the system; for the convenience of operation, a drag box and a preview box may be further provided, and users may move the rendered image file to be imported into the drag box, and the system may display the corresponding rendered image in the preview box. If the user is not satisfied with the current rendered image, the user may move a new rendered image file to be imported into the drag box, and the rendered image displayed in the preview box may change accordingly.

[0130] It is understandable that the above are just two examples, and system developers can choose any one or more implementation methods of importing rendered images. For example, the system may only support importing rendered images or only support generating rendered images based on 3D models, or support both methods.

[0131] S220: Analyze clothing elements and model elements of the rendered image.

[0132] In this embodiment, the model elements include the model's skin color, expression, movement, face shape, hairstyle, figure and / or makeup; the clothing elements include the outline, texture, color and / or style of the clothing.

[0133] Parsing of model elements and / or clothing includes but is not limited to the following methods: one is based on a preset specified method, and the other is based on an image parsing algorithm such as machine learning parsing.

[0134] If the system obtains the selected picture based on three-dimensional modeling of clothing and models to generate a three-dimensional model, and rendering the three-dimensional model to obtain a rendered picture, then the system can support either preset specification or machine learning analysis, or both, to analyze the rendered picture at the same time.

[0135] The preset designation method is mainly based on 3D model data and is implemented by configuring modeling tags. For example, regarding model elements, it includes various element details and attributes, such as round face, square face, and other face shapes; long hair, short hair, wavy hair, and other hairstyles; body shapes such as tall, short, fat, and thin; heavy makeup, light makeup, and no makeup, etc. Regarding clothing elements, it includes various element details and attributes, such as plaid, stripes, wavy textures, and other textures; red, yellow, blue, and other text colors or Pantone color card colors or RGB colors, etc.; set clothing suitable for commuting, professional, casual, and all-match styles; the modeling tags corresponding to the above-mentioned various element details will have corresponding preset modeling data, so that users can preview the approximate effect after modifying the modeling.

[0136] The analysis method based on machine learning algorithms mainly uses algorithms to output rendered images, and outputs analysis information of models and clothing based on a multi-task output neural network method. In addition, the machine learning algorithm can adjust the accuracy of the analysis according to different actual conditions.

[0137] The machine learning algorithm has greater parsing flexibility. For example, the preset designation method takes into account the hairstyle modeling label in advance. Then, when the user makes subsequent changes to the hairstyle, the modeling label can be directly used to perform related operations, which will bring better modification accuracy. However, if the preset designation method does not take into account the hair color modeling label, then the user will not be able to use the known modeling label to modify the hair color. The types of pre-configured modeling labels are related to the ability of 3D modeling. If the modeling software does not support the selection and modeling of hair color, then it is naturally impossible to pre-define the relevant modeling labels. The use of machine learning algorithms can make up for this, because the machine learning algorithm does not rely on the ability of 3D modeling to parse the rendered image, but directly parses the image itself, so it can parse out the elements that cannot be pre-configured with modeling labels. Therefore, in terms of accuracy, the preset designated modeling label is the specific modeling part of the corresponding 3D modeling, the rendered image is obtained from the 3D modeling, and the machine learning algorithm automatically recognizes the image, so the preset designation method is usually more accurate.

[0138] In short, the method proposed in this embodiment can support multiple element parsing methods, which can be selected by users according to actual needs. For example, when the rendered image is based on three-dimensional modeling rendering, the user can only use preset specifications, or only use machine learning algorithms, or use both preset specifications and machine learning algorithms to parse the rendered image.

[0139] S230: Modify the rendered image by adjusting clothing elements, model elements and / or adding new elements to obtain a finished image.

[0140] In this step, this embodiment will use the human-computer interaction interface to enable the user to input the adjustment elements and add new elements, such as providing an element editing interface. Specifically, several options can be provided on the human-computer interaction interface. For the model element, it will provide element detail options related to the model detail elements such as skin color, hairstyle, makeup, etc. Corresponding to the above element detail options, it will further provide attribute options. For example, when the model detail element selected by the user is skin color, the attribute option will display attribute options related to skin color such as white, yellow, and black; for clothing elements, it will also provide element detail options related to clothing elements such as texture and color. For selecting different clothing detail elements, the attribute option will further provide corresponding attributes, which will not be given as examples here;

[0141] In order to facilitate customized modification of rendered images, an editing area will be displayed in the element editing interface. The editing area includes a text input area and a picture input area. If the user wants a special hairstyle, such as when the user needs the model to have no hair, the user can enter "bald head" in the custom text input box. For example, if the user cannot describe a certain hairstyle in words, the user can drag the corresponding hairstyle picture into the picture input area to enter the adjustment command; the adjustment method of clothing elements is similar to that of model elements, so I will not go into details here.

[0142] It should be noted that the finished image obtained through step S230 can be a single image or a set of multiple images, which fully utilizes the digital modeling capabilities and does not require highly complex model modeling. At the same time, there is no need to go through traditional operations such as sample clothing, model shooting, and photo editing, thereby achieving rapid image output and content distribution.

[0143] When the user needs to obtain a set of multiple groups of pictures, the clothing elements, model elements and newly added elements can be adjusted accordingly, so that some of the elements are the same, while other elements can be changed according to the user's needs, and finally the group of pictures required by the user is generated.

[0144] For the method in this embodiment, an element that has not received a user adjustment instruction means that the element is kept the same in the multiple sets of images, that is, the sameness of some elements in the set of images is achieved.

[0145] For example, the models in the generated set of pictures may be fixed as the same by making some of the model elements the same, while changing other model elements so that the models have different expressions, movements, and postures;

[0146] The clothes in the generated set of pictures can be fixed to the same style by making some clothing elements the same, while changing other clothing elements to make the clothes have different colors and textures;

[0147] The clothing in the generated group of pictures can be fixed to the same background by keeping a part of the scene elements the same, while changing another part of the scene elements so that the scene has different perspectives.

[0148] The number of generated images selected by the user can be received, and images can be generated according to the user's needs.

[0149] In this embodiment, step S210 completes the three-dimensional modeling of the clothing and the model in the clothing modeling unit. First, 3D clothing modeling is performed. After the clothing modeling is completed, the user can select a digital model or a mannequin model to generate a three-dimensional model. Please refer to Figure 3 The three-dimensional modeling of the clothing and the model to generate the three-dimensional model in step S210 includes:

[0150] S211: Perform three-dimensional modeling on the clothing to construct a three-dimensional clothing model.

[0151] After step S211, the user can choose to execute one of step S212 and step S213.

[0152] S212: providing the user with an option to customize a digital model, and performing clothing simulation in a modeling software to generate a three-dimensional model based on the three-dimensional clothing model and the customized digital model.

[0153] S213: providing a plurality of mannequins for the user to choose from, simulating the three-dimensional clothing model and the mannequin selected by the user to a stable state through a simulation engine of a modeling software to generate a three-dimensional model.

[0154] Preferably, when generating a three-dimensional model in step S210, a scene suitable for the clothing and the model can be preset to generate a three-dimensional model including the scene. When parsing the clothing elements and model elements of the rendered image in step S220, the scene elements of the rendered image are also parsed, so that the rendered image can be modified by adjusting the scene elements in step S230. In addition, the picture scene can also be generated by directly adding scene elements in step S230.

[0155] Please refer to Figure 4 , step S230 includes:

[0156] S231: Encode the rendered image.

[0157] It should be noted that step S231 is implemented through an encoder, which can convert network calculations from image pixel space to hidden space, achieve data dimensionality reduction and compression, and reduce the amount of calculation, thereby improving the quality of model generation, better adjusting or adding various elements, and being applicable to some occasions that require special viewing angles, so as to better meet design requirements and improve efficiency. Specifically, when the rendered image is encoded through the encoder, a feature tensor is obtained. It can be understood that the feature tensor contains several eigenvalues, and different eigenvalues ​​correspond to different image elements. For example, the model's mouth and eyes will have their own eigenvalues.

[0158] S232: Modify the encoded rendering image by adjusting clothing elements, model elements and / or adding new elements to obtain a modified image.

[0159] It should be noted that the modification of the rendered image by adding new elements in step S232 includes:

[0160] Add scene elements to modify the scene of the rendered image based on the scene elements, including but not limited to the color tone, layout, matching and other elements of the scene;

[0161] and / or, adding character elements to modify the model based on the character elements, including but not limited to the model's age, gender, action, etc.;

[0162] And / or, add text information so that the text information is displayed on the rendered image. The text information may include clothing prices, current hot items, fashion trends, current affairs, and other information closely related to business.

[0163] In this embodiment, step S232 is implemented by a generative network. It should be noted that the generative network is a machine model with a learning function. The generative network can extract rules and patterns from existing data through learning based on probability models and statistical methods, and use these patterns to generate new data, such as generating new samples of images, texts, or audio data. In the above process, after receiving at least one adjustment instruction for the clothing element, the model element, and adding a new element, this embodiment selects different encoders according to the input of the adjustment instruction to generate a feature vector corresponding to the adjustment instruction.

[0164] S233: Decode the modified image to obtain a finished image.

[0165] The solution proposed in this embodiment has a wide range of applications. For example, when it is applied to the rapid customization of images on online e-commerce platforms, by processing and producing materials such as three-dimensional digital modeling clothing, models, scenes, etc., it can meet the generative AI technology steps required for content distribution in e-commerce scenarios, and can use this step to achieve the purpose of rapid and high-quality personalized customization of single images and group images for e-commerce models.

[0166] Example 3

[0167] This embodiment proposes another personalized customized drawing method, please refer to Figure 5 , the method comprising:

[0168] S310: Obtain a rendering image.

[0169] It should be noted that the rendered image contains at least model elements and clothing elements, that is, the rendered image obtained in step S310 contains at least a model and clothing, which is similar to step S210 in the embodiment. In this embodiment, the rendered image can be obtained by performing three-dimensional modeling of clothing and models to generate a three-dimensional model and rendering the three-dimensional model, or by receiving a rendered image directly imported by a user, and the rendered image directly imported by the user contains at least model elements and clothing elements.

[0170] S320: Analyze clothing elements and model elements in the rendered image.

[0171] In this embodiment, step S320 may use a preset designation and / or image analysis algorithm to analyze clothing elements and model elements in the rendered image, and the preset designation method is implemented based on the configuration modeling tag.

[0172] S330: receiving at least one adjustment instruction for clothing elements and model elements, and modifying the rendered image to obtain a finished image.

[0173] Specifically, the adjustment instruction includes but is not limited to user input including editing area, attribute options, element detail options, etc. In step S330, the modification of the rendered image may include determining the feature value to be modified based on the adjustment instruction.

[0174] Preferably, step S330 is implemented through an element editing interface. Exemplarily, the element editing interface includes at least one editing area of ​​a clothing element and a model element to receive the user's input in the editing area to confirm the adjustment instruction;

[0175] In another example, the element editing interface includes an element detail option and an attribute option to receive a user's selection input of the element detail option and / or the attribute option and confirm the adjustment instruction, the element detail option corresponds to the detail element of the clothing element and / or the model element, and the attribute option corresponds to the attribute of the detail element, wherein the element detail option corresponds to the modeling tag, and the attribute option corresponds to the element detail option;

[0176] In the process of executing step S330, this embodiment will provide the user with a quick edit option. After receiving the user enabling the quick edit option, the modeling module will further provide a specific edit target. The user can further select the edit target. According to the edit target selected by the user, the modeling module will call the corresponding edit details. The user can control the modeling module to automatically complete the modeling edit through the edit details. For example, if the user wants to perform quick edit on the eyes of the digital model, after enabling the quick edit option, the modeling module will provide a list of various parts of the digital model, including various parts that can provide quick edits, such as eyes, mouth, nose, left arm, right arm, etc. The user selects the eye button in the list, and the modeling module further provides various preset styles of eyes, such as phoenix eyes, etc., and also provides quick customization options, such as color (black, white, yellow, etc.), eye width, eye height, eye spacing, etc. It can be seen that this method will improve the input efficiency and input accuracy of the adjustment instruction;

[0177] In some embodiments, if the method of parsing the clothing elements and model elements in the rendered image in step S320 includes preset designation, that is, step S320 adopts the preset designation method to parse the clothing elements and model elements in the rendered image, or simultaneously adopts the preset designation and image parsing algorithm method to parse the clothing elements and model elements in the rendered image, the above-mentioned quick editing options correspond to the element detail options and attribute options; in other implementations, the quick editing options correspond to the element detail options, attribute options and modeling tags.

[0178] See also Figure 6 , step S330 specifically includes:

[0179] S331: Encode the rendered image to obtain an initial feature tensor of the rendered image.

[0180] The initial feature tensor obtained in step S331 includes several eigenvalues, and different eigenvalues ​​correspond to different image elements. For example, the model's mouth and eyes have their own eigenvalues.

[0181] S332: Based on the received adjustment instruction, modify some eigenvalues ​​in the initial feature tensor to form a target feature tensor.

[0182] S333: Decode the target feature tensor to obtain a finished image.

[0183] Specifically, the element editing interface includes at least one editing area of ​​clothing elements and model elements. Exemplarily, when the user inputs the adjustment instruction through the editing area, since the input in the editing area is often text or picture, it is necessary to convert the text or picture into a feature value through a text or picture encoder. If the user inputs the adjustment instruction through the attribute option or the element detail option, since the attribute of the element detail will have corresponding modeling data, then it is necessary to convert the modeling data into a feature value through a pre-trained modeling-related encoder. It can be seen that this embodiment also provides a variety of encoders to support multi-modal input; after converting the adjustment instruction into a feature value, this embodiment further merges the feature value related to the adjustment instruction with the corresponding feature value in the feature tensor of the rendered image. There are many ways of fusion, which will not be described here. For example, when the user enters the text "red eyes" through the editing area, this embodiment will convert the above text into a feature value expressing the eye color as red through a specific encoder, and find the feature value expressing the eye color from the feature tensor of the rendered image. After the above two feature values ​​are merged, the modification of the feature tensor of the rendered image is realized; thereby, the rendered image is modified.

[0184] Example 4

[0185] An embodiment of the present specification also provides an electronic device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor implements the method proposed in embodiment 2 or embodiment 3 by running the executable instructions.

[0186] Figure 7 This is a schematic diagram of a device structure provided by an exemplary embodiment. Figure 5 At the hardware level, the device includes a processor 401, an internal bus 402, a network interface 403, a memory 404, and a non-volatile memory 405, and may also include hardware required for other services. One or more embodiments of this specification may be implemented based on software, such as the processor 401 reading the corresponding computer program from the non-volatile memory 405 into the memory 404 and then running it. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0187] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0188] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0189] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0190] Example 5

[0191] The embodiments of this specification also provide a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method proposed in the above-mentioned embodiment 2 or embodiment 3 are implemented.

[0192] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0193] The present disclosure provides a method and system for enhancing the sense of reality of a virtual model based on a generative network. Based on a highly controllable generative AI technology, the method makes full use of the prior information of digital clothing and virtual models, can significantly improve the sense of reality of clothing models, while maintaining the high fidelity of modeled clothing, and is highly adaptable to the alignment of virtual models in the digital world to real-life models in the real world.

[0194] In summary, the present disclosure provides a personalized customized drawing system and method. The solution proposed in the present disclosure can realize the rapid drawing of clothing pictures with high quality, improve the efficiency of drawing and content distribution and marketing needs, maintain the high fidelity of modeled clothing, has low operating difficulty, significantly reduces time and labor costs, and has a relatively wide range of applications.

[0195] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

[0196] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0197] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0198] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0199] It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of this specification, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0200] The above description is merely a preferred embodiment of one or more embodiments of the present specification and is not intended to limit one or more embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present specification shall be included in the scope of protection of one or more embodiments of the present specification.

Claims

1. A personalized customized drawing system, characterized in that: The system comprises: A modeling module, used for three-dimensional modeling of clothing and models to generate a three-dimensional model; A rendering module, used for rendering the three-dimensional model to obtain a rendered image; A parsing module, used for parsing clothing elements and model elements of the rendered image; The modification module is used to modify the rendered image by adjusting the clothing elements, the model elements and / or adding new elements to obtain a finished image.

2. The personalized customized drawing system according to claim 1, characterized in that: The modeling module includes: A clothing modeling unit, used for performing three-dimensional modeling on the clothing to construct a three-dimensional clothing model; A model modeling unit is used to provide the user with the option of customizing a digital model, and based on the three-dimensional clothing model and the customized digital model, perform clothing simulation in the modeling software to generate the three-dimensional model; or to provide the user with a plurality of mannequins for the user to choose from, and simulate the three-dimensional clothing model and the mannequin selected by the user to a stable state through a simulation engine of the modeling software to generate the three-dimensional model.

3. The personalized customized drawing system according to claim 1 or 2, characterized in that: The modeling module further includes a scene modeling unit, which is used to preset a scene suitable for the clothing and the model when generating the three-dimensional model, so as to generate the three-dimensional model including the scene; The parsing module comprises: A clothing parsing unit, used for parsing clothing elements of the rendered image; A model parsing unit, used for parsing model elements of the rendered image; A scene parsing unit is used to parse the scene elements of the rendered image.

4. The personalized customized drawing system according to claim 1, characterized in that: The modification module comprises: An encoder, used for encoding the rendered image; An adjustment unit, used for modifying the encoded rendering image by adjusting the clothing elements, the model elements and / or adding new elements to obtain a modified image; A decoder is used to decode the modified image to obtain the finished image.

5. A personalized customized drawing method, characterized in that: The method comprises: Performing three-dimensional modeling on the clothing and the model to generate a three-dimensional model, and rendering the three-dimensional model to obtain a rendered image; Analyzing clothing elements and model elements of the rendered image; The rendered image is modified by adjusting the clothing elements, the model elements and / or adding new elements to obtain a finished image.

6. The personalized customized drawing method according to claim 5, characterized in that: The method further comprises: When generating the three-dimensional model, presetting a scene suitable for the clothing and the model to generate the three-dimensional model including the scene; When parsing the clothing elements and model elements of the rendered image, the scene elements of the rendered image are also parsed, so that the rendered image can be modified by adjusting the scene elements.

7. The personalized customized drawing method according to claim 5, characterized in that: The modifying the rendered image by adjusting the clothing elements, the model elements and / or adding new elements to obtain a finished image includes: Encoding the rendered image; Modifying the encoded rendering image by adjusting the clothing element, the model element and / or adding a new element to obtain a modified image; The modified picture is decoded to obtain the finished picture.

8. The personalized customized drawing method according to claim 5 or 7, characterized in that: The modifying of the rendered image by adding new elements includes: Adding scene elements to modify the scene of the rendered image based on the scene elements; and / or, adding character elements to modify the model based on the character elements; And / or, adding text information so that the text information is displayed on the rendered image.

9. The personalized customized drawing method according to any one of claims 5 to 7, characterized in that: The model elements include the model's skin color, expression, movement, face shape, hairstyle, figure and / or makeup; The clothing elements include the silhouette, texture, color and / or style of the clothing.

10. The personalized customized drawing method according to claim 5, characterized in that: The three-dimensional modeling of the clothing and the model to generate the three-dimensional model comprises: Performing three-dimensional modeling on the garment to construct a three-dimensional garment model; Providing the user with the option of customizing a digital model, and based on the three-dimensional clothing model and the customized digital model, performing clothing simulation in the modeling software to generate the three-dimensional model; or providing the user with a plurality of mannequins for the user to choose from, simulating the three-dimensional clothing model and the mannequin selected by the user to a stable state through a simulation engine of the modeling software to generate the three-dimensional model.

11. A personalized customized drawing method, characterized in that: The method comprises: Obtaining a rendered image; the rendered image at least includes a model element and a clothing element; parsing the clothing elements and the model elements in the rendered image; At least one adjustment instruction for the clothing element and the model element is received, and the rendered image is modified to obtain a finished image.

12. The personalized customized drawing method according to claim 11, characterized in that: The "obtaining a rendered image" includes: Performing three-dimensional modeling on clothing and models to generate a three-dimensional model, and rendering the three-dimensional model to obtain a rendered image; Or, receive rendered images imported by users.

13. The personalized customized drawing method according to claim 11, characterized in that: The “analyzing clothing elements and model elements in the rendered image” includes: The clothing elements and the model elements in the rendered image are analyzed by using a preset designated and / or image analysis algorithm.

14. The personalized customized drawing method according to claim 11, characterized in that: The method further comprises: Displaying an element editing interface; the element editing interface includes at least one editing area of ​​the clothing element and the model element; Receive the user's input in the editing area and confirm the adjustment instruction.

15. The personalized customized drawing method according to claim 11 or 13, characterized in that: The method further comprises: Displaying an element editing interface; the element editing interface includes element detail options and attribute options; Receive user selection input for element detail options and / or attribute options, and confirm the adjustment instruction.

16. The personalized customized drawing method according to claim 11, characterized in that: The "receiving at least one adjustment instruction for the clothing element and the model element, and modifying the rendered image to obtain a finished image" includes: Encoding the rendered image to obtain an initial feature tensor of the rendered image; Based on the received adjustment instruction, modify some eigenvalues ​​in the initial feature tensor to form a target feature tensor; The target feature tensor is decoded to obtain the finished image.

17. The personalized customized drawing method according to claim 15, characterized in that: The preset designation mode is implemented based on a configuration modeling tag, and the method further includes: If the method of parsing the clothing elements and the model elements in the rendered image includes preset designation, the element detail options correspond to the modeling tags.

18. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 6 to 17 by running the executable instructions.

19. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 6 to 17 are implemented.

Images