CN113051778B

CN113051778B - Garment design method, device, electronic equipment and storage medium

Info

Publication number: CN113051778B
Application number: CN202110518507.6A
Authority: CN
Inventors: 魏辰峰; 陈达勤; 浣军; 李曈; 娄明; 宋博宁
Original assignee: Beijing Huimei Future Technology Co ltd
Current assignee: Beijing Huimei Future Technology Co ltd
Priority date: 2021-05-12
Filing date: 2021-05-12
Publication date: 2024-01-16
Anticipated expiration: 2041-05-12
Also published as: CN113051778A

Abstract

The application provides a garment design method, a garment design device, electronic equipment and a storage medium, and relates to the field of garment design. The method comprises the steps of taking a received design request as input of a first model trained in advance to operate, so as to obtain a plurality of clothing design pictures; counting a plurality of clothing commodities which are popular in the clothing class corresponding to the design request; extracting common characteristics of a plurality of clothing commodities to obtain target characteristics; calculating the feature similarity between the corresponding feature of each picture in the multiple clothing design pictures and the target feature; and sending at least one clothing design picture with the highest feature similarity between the features and the target features to the client so as to carry out clothing design according to the at least one clothing design picture. The garment design method, the device, the electronic equipment and the storage medium can generate the garment with the appointed design points according to the requirements.

Description

Garment design method, device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of garment design, and in particular, to a garment design method, a device, an electronic apparatus, and a storage medium.

Background

As machine learning techniques and image generation techniques mature, machine learning is increasingly being used in apparel design. In particular, the challenge-generating network (Generative Adversarial Networks, GAN) technology that emerged in 2014 has been able to generate very realistic and high resolution garment images, and most of these technologies use multi-dimensional normal distributed sampling gaussian noise as the input to the GAN model, which is subjected to a series of operations to obtain very realistic images.

However, such approaches have a common disadvantage of lacking control, namely difficulty in controlling the creation of garments of a given design point.

Therefore, how to provide an effective solution to ensure that a garment with a specified design point can be produced is a challenge in the prior art.

Disclosure of Invention

The embodiment of the application provides a garment design method, a device, electronic equipment and a storage medium, which are used for solving the problem that garments with appointed design points are difficult to generate in the prior art.

The embodiment of the application adopts the following technical scheme:

in a first aspect, an embodiment of the present application provides a method for designing a garment, including:

calculating the received design request as input of a first model trained in advance to obtain a plurality of clothing design pictures;

counting a plurality of clothing commodities which are popular currently in clothing classes corresponding to the design request;

extracting common characteristics of the plurality of clothing commodities to obtain target characteristics;

calculating the feature similarity between the feature corresponding to each picture in the multiple clothing design pictures and the target feature;

at least one clothing design picture with the highest feature similarity between the features and the target features is sent to a client so as to carry out clothing design according to the at least one clothing design picture;

the design request comprises a clothing type and clothing style parameters, and the first model is obtained by training with a known first design picture as an output and the clothing type and clothing style parameters corresponding to the first design picture as inputs.

In one possible design, the counting the plurality of articles of clothing currently popular in the clothing class corresponding to the design request includes:

counting commodity sales of clothing commodities of clothing classes corresponding to the design request in a current time period according to clothing commodity sales records of a third party server;

and selecting the multiple clothing commodities with the highest commodity sales volume as the currently popular multiple clothing commodities.

In one possible design, the extracting the common features of the plurality of articles of clothing to obtain the target features includes:

respectively calculating the pictures of the multiple clothing commodities as the input of a pre-trained second model, and splicing the feature vectors output by the last two layers of the second model to obtain multiple initial features corresponding to the multiple clothing commodities one by one;

extracting feature vectors common to the plurality of initial features to obtain the target features;

the second model is obtained by training with a known second clothing design picture as an input and clothing items corresponding to the second clothing design picture as an output.

In one possible design, the method further comprises:

invoking a third model corresponding to the clothing class;

calculating the selected target clothing design picture in at least one clothing design picture as the input of the third model to obtain a plate parameter corresponding to the target clothing design picture;

3D rendering is carried out on the target clothing design picture according to the slab parameters;

the third model is obtained by training with a known third clothing design picture as an input and a sheet parameter of the third clothing design picture as an input.

In one possible design, the 3D rendering of the target garment design picture according to the panel parameters includes:

3D rendering is carried out on the target clothing design picture according to the slab parameters and the generated fabric; or (b)

And 3D rendering is carried out on the target clothing design picture according to the slab parameters and the generated printing.

In one possible design, the method further comprises:

responding to the adjustment operation of the client side on the plate parameters to adjust the plate parameters;

the 3D rendering of the target garment design picture according to the panel parameters includes:

and performing 3D rendering on the target clothing design picture according to the adjusted plate parameters.

In one possible design, the first model is a styleGAN model or a BigGAN model.

In a second aspect, embodiments of the present application provide a garment design apparatus, comprising:

the first operation unit is used for performing operation by taking the received design request as the input of a first model trained in advance to obtain a plurality of clothing design pictures;

the statistics unit is used for counting a plurality of currently popular clothing commodities in clothing classes corresponding to the design request;

the extraction unit is used for extracting the common characteristics of the plurality of clothing commodities to obtain target characteristics;

the second operation unit is used for calculating the feature similarity between the feature corresponding to each of the multiple clothing design pictures and the target feature;

the sending unit is used for sending at least one clothing design picture with the highest feature similarity between the features and the target features to the client so as to carry out clothing design according to the at least one clothing design picture;

In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the bus;

a memory for storing a computer program;

and the processor is used for executing the programs stored in the memory and realizing the following processes:

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, the computer program when executed by a processor implementing the following procedures:

The above-mentioned at least one technical scheme that one or more embodiments of this application adopted can reach following beneficial effect:

the design request is used as the input operation of the first model to obtain a plurality of clothing design pictures, a plurality of currently popular clothing commodities in clothing types corresponding to the design request are counted, common characteristics of the plurality of clothing commodities are extracted to obtain target characteristics, and then at least one clothing design picture with the highest characteristic similarity between the characteristics and the target characteristics is sent to a client so as to carry out clothing design according to the at least one clothing design picture, the design request comprises clothing type and clothing style parameters, and the clothing design picture sent to the client meets the clothing type and the clothing style parameters and simultaneously has the highest characteristic matching degree with the currently popular clothing commodities, so that clothing with specified design points can be generated according to requirements.

Drawings

The accompanying drawings, which are included to provide a further understanding of the present document, illustrate and explain the present document, and are not to be construed as limiting the document. In the drawings:

fig. 1 is a schematic flowchart of a method for designing a garment according to an embodiment of the present application.

Fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Fig. 3 is a schematic structural diagram of a garment design apparatus according to an embodiment of the present application.

Detailed Description

In order to solve the problem that it is difficult to generate a garment with a specified design point in the prior art, the embodiments of the present application provide a garment design method, device, electronic device, and storage medium, where the design method, device, electronic device, and storage medium can generate a garment with a specified design point according to requirements.

The garment design method provided by the embodiment of the application can be applied to a server, and the server can be a network server or a database server.

For convenience of description, the embodiments of the present application will be described with the server as the execution body, except for the specific description.

It is understood that the execution bodies do not constitute limitations on the embodiments of the present application.

Optionally, as shown in fig. 1, the method for designing the garment may include the following steps:

step S101, the received design request is used as input of a first model trained in advance to operate, and a plurality of clothing design pictures are obtained.

Wherein the design request includes a garment type and a garment style parameter. For example, the garment type may be T-shirts, skirts, shorts, etc., and the garment style parameters may be holes, water washes, heben style, etc.

In this embodiment, a first model for generating a design image of a garment is trained in advance, where the first model is obtained by training with a known first design image as an output and a garment type and a garment style parameter corresponding to the first design image as inputs. The known first service design picture can be used for carrying out clothing data grabbing aiming at electronic commerce, sales space and running and showing data through a crawler tool, tiling/tiling classification is carried out on the grabbed images through a classification network, background noise is removed aiming at a tiling picture through a semantic segmentation algorithm, and then patterns and prints on the clothing are erased, so that a clean standard effect picture, namely the first service design picture, is obtained.

When the clothing is designed, the design request (clothing type and clothing style parameters) can be quantized, and the quantized design request is used as the input of the first model to operate, so that a plurality of clothing design pictures are obtained.

In the embodiment of the present application, the first model may be, but is not limited to, a styleGAN model, a BigGAN model, or a conditional generation-antagonism network (Conditional Generative Adversarial Networks, CGAN) model, etc.

Step S102, counting a plurality of clothing items popular in the clothing class corresponding to the design request.

Specifically, counting and designing a plurality of clothing items popular in the clothing class corresponding to the request may include the following steps:

and S1021, counting commodity sales of clothing commodities of clothing classes corresponding to the design request in the current time period according to the clothing commodity sales records of the third party server.

The third party service end can be a server of a clothing commodity sales platform, such as a server of a Taobao platform, a server of a Beijing east platform and the like. The current time period may be set according to practical situations, such as the first 1 month or 1 week of the current time. The clothing items may refer to clothing types, for example, in the field of clothing design, a skirt may be considered as one item, and a shirt may be considered as another item different from the one corresponding to the skirt, so that the clothing item corresponding to the design request may refer to the clothing type carried in the design request.

For example, the type of clothing carried in the design request is a skirt, the current time period is the previous week of the current time, and counting the sales of clothing items corresponding to the design request in the current time period may refer to counting the sales of various skirts in the previous week.

Step S1022, selecting the clothing articles with the highest commodity sales as the currently popular clothing articles.

After the commodity sales of the clothing commodities of the clothing class corresponding to the design request in the current time period are counted, the clothing commodities of different styles can be ordered according to the sales according to the clothing styles, and then the clothing commodities with the highest commodity sales are selected as the current popular clothing commodities.

For example, the top 100 items of clothing with the highest sales volume may be selected as the currently popular items of clothing, and the items of clothing with the top 1% of sales volume may be selected as the currently popular items of clothing.

And step S103, extracting common features of a plurality of clothing commodities to obtain target features.

In this embodiment of the present application, a second model for extracting the commodity feature is also pre-established, where the second model may be obtained by training with a known second clothing design picture as input and clothing items corresponding to the second clothing design picture as output.

When the common features of the multiple clothing articles are extracted, the pictures of the multiple clothing articles can be respectively used as the input of the pre-trained second model to be operated, and the feature vectors output by the last two layers of the second model are spliced to obtain multiple initial features corresponding to the multiple clothing articles one by one. And extracting feature vectors shared by the plurality of initial features to obtain target features, wherein the target features are the shared features of the plurality of clothing commodities.

For example, there are 3 types of clothing articles, which are respectively denoted as clothing article a, clothing article B and clothing article C, wherein when the picture of clothing article a is calculated as input of the second model, the feature vectors outputted by the last two layers of the second model are respectively a1 and a2, when the picture of clothing article B is calculated as input of the second model, the feature vectors outputted by the last two layers of the second model are respectively B1 and B2, and when the picture of clothing article C is calculated as input of the second model, the feature vectors outputted by the last two layers of the second model are respectively C1 and C2. Then the feature vector a1 and the feature vector a2 can be spliced to obtain a feature vector a3, the feature vector b1 and the feature vector b2 can be spliced to obtain a feature vector b3, the feature vector c1 and the feature vector c2 can be spliced to obtain a feature vector c3, and then the feature vector shared by the feature vectors a3, b3 and c3 is extracted to obtain the target feature.

In this embodiment of the present application, the second clothing design picture may be the aforementioned first clothing design picture, or may be a clothing design picture obtained according to the aforementioned method for obtaining the first clothing design picture, which is not specifically limited in this embodiment of the present application.

The second model may be, but is not limited to, a styleGAN model, a BigGAN model, or a conditional generation-antagonism network (Conditional Generative Adversarial Networks, CGAN) model, or the like.

Step S104, calculating the feature similarity between the feature corresponding to each picture in the multiple clothing design pictures and the target feature.

In the embodiment of the present application, when calculating the feature similarity between the feature corresponding to each picture and the target feature, the similarity between the features may be obtained by calculating the KL (Kullback-Leibler) distance, JS (Jensen-Shannon) distance or cosine distance between the feature corresponding to each picture and the target feature, and performing a weighting operation according to the weights after normalization, which is not specifically described in the embodiment of the present application in the prior art.

Step S105, at least one clothing design picture with the highest feature similarity between the features and the target features is sent to the client.

After receiving the transmitted at least one clothing design picture, the client can carry out clothing design according to the at least one clothing design picture.

According to the clothing design method provided by the embodiment of the application, the design request is used as the input operation of the first model to obtain a plurality of clothing design pictures, a plurality of currently popular clothing commodities in clothing types corresponding to the design request are counted, common characteristics of the plurality of clothing commodities are extracted to obtain target characteristics, then at least one clothing design picture with the highest characteristic similarity between the characteristics and the target characteristics is sent to the client so as to carry out clothing design according to the at least one clothing design picture, the design request comprises the clothing type and the clothing style parameters, the clothing design picture sent to the client meets the clothing type and the clothing style parameters, and meanwhile, the characteristics of the clothing design picture are matched with the same characteristics of the plurality of currently popular clothing commodities, so that clothing with specified design points can be generated in a supervision mode according to requirements, and the clothing design can be carried out for all the clothing types in the market basically. Meanwhile, the generation process of the clothing design picture is convenient and quick, and the clothing design efficiency is improved.

On the basis of the method for designing a garment according to the first aspect, an embodiment of the present application further provides a possible design one for performing 3D rendering on a garment design picture. Which may include, but is not limited to, the following steps:

step S201, a third model corresponding to the clothing class is called.

In this embodiment of the present invention, a plurality of third models are pre-established for different types of clothing design pictures, where the third models are used to determine panel parameters of the different types of clothing design pictures, and the third models are obtained by training with known third clothing design pictures as input and panel parameters of the third clothing design pictures as input. The third model may be, but is not limited to, a styleGAN model, a BigGAN model, or a conditional generation-antagonism network (Conditional Generative Adversarial Networks, CGAN) model, etc.

Wherein, the panel parameters can include, but are not limited to, panel seam point position, panel vertex position, radian between panel points, panel side length, panel printing position, etc.

After the server sends at least one clothing design picture to the client, the server can call a third model corresponding to the clothing class in the design request.

In this embodiment of the present application, the third clothing design picture may be the first clothing design picture or the second clothing design picture, or may be a clothing design picture obtained according to the foregoing manner of obtaining the first clothing design picture, which is not specifically limited in this embodiment of the present application.

Step S202, the selected target clothing design picture in the at least one clothing design picture is used as the input of the third model to operate, and the plate parameters corresponding to the target clothing design picture are obtained.

In this embodiment of the present application, after the server sends at least one clothing design picture to the client, the client user may select one or more of the clothing design pictures as a target clothing design picture according to the need.

And step S203, performing 3D rendering on the target clothing design picture according to the plate parameters.

Further, when 3D rendering is performed on the target clothing design picture, different fabrics can be generated or corresponding fabrics can be generated according to the selection of the user, and then 3D rendering is performed on the target clothing design picture according to the panel parameters and the generated fabrics.

Alternatively, different kinds of prints may be generated or corresponding prints may be generated according to the user's selection, and then 3D rendering of the target garment design picture is performed according to the panel parameters and the generated prints.

Furthermore, before 3D rendering is performed on the target clothing design picture, the user can initiate adjustment operation for the panel parameters to the server through the client, the server responds to the adjustment operation of the client for the panel parameters to adjust the panel parameters, and 3D rendering can be performed on the target clothing design picture according to the adjusted panel parameters during 3D rendering, so that the commercially generated standard is achieved.

Thus, through the possible design one, 3D clothing effects of different fabrics or different prints can be generated during 3D rendering so as to guide the production of customers. Meanwhile, the parameters of the plate sheet of the clothing design picture can be adjusted, so that the standards which can be generated commercially are achieved.

Fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 2, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.

The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 2, but not only one bus or type of bus.

And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.

The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs to form the garment design device on a logic level. The processor is used for executing the programs stored in the memory and is specifically used for executing the following operations:

The method performed by the garment design apparatus disclosed in the embodiment shown in fig. 2 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in one or more embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with one or more embodiments of the present application may be embodied directly in a hardware decoding processor or in a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

The electronic device may also execute the method of fig. 1 and implement the functions of the garment design apparatus in the embodiment shown in fig. 2, which is not described herein.

Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flow is not limited to each logic unit, but may be hardware or a logic device.

The embodiments also provide a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device comprising a plurality of application programs, enable the electronic device to perform the method of the embodiment of fig. 1, and in particular to perform the following operations:

Fig. 3 is a schematic structural view of a garment design apparatus according to an embodiment of the present application. Referring to fig. 3, in one software embodiment, a garment design apparatus includes:

In summary, the foregoing description is only a preferred embodiment of the present document, and is not intended to limit the scope of the present document. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this document should be included within the scope of protection of this document.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer 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 Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

All embodiments in this document are described in a progressive manner, and identical and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described as different from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

Claims

1. A method of designing a garment, comprising:

2. The method of claim 1, wherein counting a plurality of articles of apparel currently popular in the apparel class corresponding to the design request comprises:

3. The method of claim 1, wherein extracting the common features of the plurality of items of clothing to obtain the target features comprises:

the second model is obtained by training with a known second clothing design picture as input and initial characteristics corresponding to the second clothing design picture as output.

4. The method according to claim 1, wherein the method further comprises:

invoking a third model corresponding to the clothing class;

the third model is obtained by training with a known third clothing design picture as an input and a sheet parameter of the third clothing design picture as an output.

5. The method of claim 4, wherein the 3D rendering of the target apparel design picture in accordance with the panel parameters comprises:

6. The method according to claim 4, wherein the method further comprises:

7. The method of claim 1, wherein the first model is a styleGAN model or a BigGAN model.

8. A garment design apparatus, comprising:

9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the bus;

a memory for storing a computer program;

10. A computer readable storage medium, wherein a computer program is stored in the storage medium, the computer program realizing the following flow when executed by a processor: