CN114357544A - Fashion design system and method for clothes - Google Patents
Fashion design system and method for clothes Download PDFInfo
- Publication number
- CN114357544A CN114357544A CN202111455629.1A CN202111455629A CN114357544A CN 114357544 A CN114357544 A CN 114357544A CN 202111455629 A CN202111455629 A CN 202111455629A CN 114357544 A CN114357544 A CN 114357544A
- Authority
- CN
- China
- Prior art keywords
- fashion
- model
- design
- artificial intelligence
- elements
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of intelligent clothing manufacturing, and discloses a fashion design system and a fashion design method for clothing, which comprise a fashion acquisition unit, a fashion processing unit, a fashion design unit and a fashion generation unit; the fashion acquisition unit is used for acquiring various fashion elements; the fashion processing unit is used for counting and learning fashion elements by using a deep learning algorithm; the fashion design unit is used for separating and reclassifying the clothing attributes representing the fashion elements; the fashion generation unit is used for generating clothes by referring to semantic or environmental conditions. According to the invention, through restrictive condition input, the style of the garment can be automatically designed according to an artificial intelligence algorithm, so that a great deal of time and labor are saved. In the fashion field, the clothes can be freely customized according to the requirements of users comprehensively, the design cost is greatly reduced, and the design efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of intelligent clothes, and particularly relates to a fashion design system and method for clothes.
Background
At present, in the field of fashion design, designers often design new clothes through their own learning experience, and each time a piece of clothes is designed, a lot of time and energy are consumed, and it is impossible for designers to design clothes of each style as required. Therefore, in the fashion field, the clothes are designed according to requirements, and a potential and huge application scene is provided.
The design system of the personal customized fashion clothing disclosed in the Chinese patent with the publication number of CN108606384A is characterized in that sliding blocks are arranged outside vertical plates on the left side and the right side in a sliding mode, and the width of limbs with different heights is rapidly measured for a customer to design clothing. Chinese patent application No. CN201910495710.9, "cognitive automation and interactive personalized fashion design," employs training a computer model by a computer device using deep learning based computer vision, identifying using a cognitively determined fashion score (F-score), creating a new fashion design using the computer model and the identified, this method does not incorporate various style features, and the designed apparel has limitations.
Disclosure of Invention
The invention aims to provide a garment fashion design system and method, which can realize garment fashion design based on artificial intelligence, greatly improve design efficiency and reduce garment design difficulty.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a fashion design system comprises a fashion acquisition unit, a fashion processing unit, a fashion design unit and a fashion generation unit;
the fashion acquisition unit is used for acquiring various fashion elements;
the fashion processing unit is used for counting and learning fashion elements by using a deep learning algorithm;
the fashion design unit is used for separating and reclassifying the clothing attributes representing fashion elements;
the fashion generation unit is used for generating clothes by referring to semantic or environmental conditions.
In a preferred scheme, the fashion processing unit comprises a training module, a three-dimensional model is built for collected fashion elements in the training module, the three-dimensional model is marked manually, parameter adaptation is carried out on the manually marked model according to input parameters to form a sample set, and the sample set is sent to a deep learning algorithm for training to obtain an artificial intelligent model.
In a preferred scheme, the fashion design unit comprises an artificial intelligence model for operating the input three-dimensional model and the input parameters, the artificial intelligence model gives fashion evaluation, and data are transmitted to the fashion generation unit.
In the preferred scheme, the fashion design unit comprises an artificial intelligence model for operating an input three-dimensional model and input parameters, the artificial intelligence model gives fashion evaluation, elements are decomposed and then fused and recombined, a sample generated after fusion and recombination is divided into two parts, one part is sent into an artificial mark, parameter adaptation is carried out on the artificial mark model according to the input parameters to form a sample set, the sample set is sent into a deep learning algorithm for training, the artificial intelligence model is iterated, and the other part is directly sent into the artificial intelligence model for fashion evaluation.
In the preferred scheme, the element decomposition includes element disassembly and plane mapping, and the disassembled elements and the mapped plane graph are combined in a combiner through one or more operations of shape, pattern, color, position, scaling, turning, distortion and array, and then subjected to stereo reconstruction, so as to realize the fusion and recombination of the design elements.
In the preferred scheme, the artificial intelligence model comprises a classifier, a semantic recognizer, an adapter and a clustering device;
the classifier is used for classifying the three-dimensional model, and the classification is associated with the semantic keywords identified by the semantic identifier;
the semantic recognizer is used for converting the input parameters into semantic keywords, and the semantic keywords are associated with the classification of the classifier;
the adapter is used for adapting the sample of the three-dimensional model according to the semantic keywords to adapt the three-dimensional model conforming to the semantic keywords;
the clustering device is used for aggregating the adapted three-dimensional models according to fashion classification and generating fashion evaluation.
In a preferred scheme, the fashion acquisition unit is provided with a three-dimensional model database.
A design method adopting the fashion design system comprises the following steps:
s1, inputting limiting parameters, and reading the stereo model data by the artificial intelligence model;
the artificial intelligence model is obtained after artificial marking, parameter adaptation and model training;
s2, carrying out fashion evaluation on the stereoscopic model according to the limited parameters;
s3, sending the design with higher fashion ticket evaluation to a fashion generation unit;
through the steps, fashion design based on artificial intelligence is achieved.
In a preferred scheme, the step S2 further includes the steps of element decomposition, fusion and recombination, so as to generate a new sample, wherein a part of the new sample is used for iteration of the artificial intelligence model after artificial labeling, parameter adaptation and model training, and the other part of the new sample is sent to the artificial intelligence model for processing;
the element decomposition and fusion recombination steps comprise:
s21, performing element disassembly on the design elements, wherein the elements comprise shapes, patterns, colors and positions;
performing plane mapping on the three-dimensional model;
s22, subjecting the disassembled elements to one or more of zooming, turning, twisting and displaying or combining a plane structure;
and S23, carrying out three-dimensional reconstruction on the combined planar structure to realize fusion and recombination.
In the preferred scheme, the artificial intelligence model comprises a classifier, a semantic recognizer, an adapter and a clustering device;
the classifier is used for classifying the three-dimensional model according to the keywords;
the semantic recognizer is used for converting the input parameters into keywords;
the adapter is used for associating the classified three-dimensional models according to the keywords;
and the clustering device is used for clustering the correlated three-dimensional models according to fashion evaluation.
Compared with the prior art, the fashion design system and the fashion design method provided by the invention have the following beneficial effects:
(1) the novel fashion design system and the novel fashion design method provided by the invention can automatically design the style of the clothes according to an artificial intelligence algorithm through the input of the constraint condition, thereby saving a large amount of time and manpower. In the fashion field, the clothes can be freely customized according to the requirements of users comprehensively, the design cost is greatly reduced, and the design efficiency is improved.
(2) The invention adopts the three-dimensional model data, is more visual and is convenient for the selection of customers. And the adoption of the three-dimensional model data is more convenient for subsequent modification and model design, and is convenient for designing and producing high-quality fashion clothes.
(3) The novel fashion design system and the method provided by the invention can be applied to online application and embedded equipment, and greatly improve the practicability.
Drawings
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
fig. 1 is a flow chart of the fashion design system and method of the present invention.
Fig. 2 is a schematic flow chart of the fashion design system and method of the present invention.
Fig. 3 is a schematic flow chart of adding a new fashion design sample to the garment of the present invention.
FIG. 4 is a functional block diagram of an artificial intelligence model of the present invention.
Detailed Description
Example 1:
in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Referring to fig. 1, a fashion design system includes a fashion acquisition unit, a fashion processing unit, a fashion design unit, and a fashion generation unit;
the fashion acquisition unit is used for acquiring various fashion elements;
the fashion processing unit is used for counting and learning fashion elements by using a deep learning algorithm;
the fashion design unit is used for separating and reclassifying the clothing attributes representing fashion elements;
the fashion generation unit is used for generating clothes by referring to semantic or environmental conditions.
The preferred scheme is as shown in fig. 2, the fashion processing unit comprises a training module, in the training module, a three-dimensional model is built for collected fashion elements, the built three-dimensional model can be closer to a real design, particularly the defect that the fashion design is better but the version design is insufficient in the later manufacturing process can be avoided, preferably, the built three-dimensional model is realized in a mode of cutting, slicing and three-dimensional splicing, although the workload of the initial three-dimensional model is increased, the subsequent workload becomes very light, and the fashion elements with different designs can be freely combined and the final effect can be conveniently evaluated. The three-dimensional model is marked manually, and the purpose of manual marking is to define the three-dimensional model according to parameters so as to facilitate the training of subsequent artificial intelligent models, such as distinguishing spring and autumn clothes, summer clothes and winter clothes, distinguishing underwear and coats, distinguishing upper clothes and lower clothes, distinguishing accessories and the like, distinguishing body type suitability, and giving fashion evaluation to different collocations.
And carrying out parameter adaptation on the artificial mark model according to the input parameters to form a sample set, and sending the sample set into a deep learning algorithm for training to obtain an artificial intelligent model. In the artificial intelligence model, the fashion evaluation values of the three-dimensional models of different inputs are obtained through adaptation. In the artificial intelligence model, selection is performed not only according to input parameters, but also a fashion evaluation value is obtained according to evaluation of the stereoscopic model by an artificially labeled sample.
A preferred embodiment is shown in fig. 2, in which the fashion design unit includes an artificial intelligence model that operates the input three-dimensional model and the input parameters, the artificial intelligence model gives a fashion evaluation, and transmits data to the fashion generation unit. And a fashion generation unit which generates a plane or a three-dimensional figure for display according to the sequence of fashion evaluation and adds elements for setting off the atmosphere, such as a mannequin, accessories outside the three-dimensional model, atmosphere lighting, flashing light and the like, in the display process.
The preferred scheme is as shown in fig. 2, the fashion design unit comprises an artificial intelligence model for operating an input three-dimensional model and input parameters, the artificial intelligence model gives fashion evaluation, elements are decomposed and then fused and recombined, a sample generated after fusion and recombination is divided into two parts, one part is sent into an artificial mark, the artificial mark model is subjected to parameter adaptation according to the input parameters to form a sample set, the sample set is sent into a deep learning algorithm for training, and iteration is carried out on the artificial intelligence model; the artificial mark is fed to help the artificial intelligence model to be iterated through artificial interference so as to improve the evaluation accuracy. And the other part is directly sent into an artificial intelligence model for fashion evaluation. By the scheme, more fashionable design samples can be obtained, or more stereo model data can be obtained to obtain more selectable results after corresponding parameters are input subsequently.
In a preferred scheme, as shown in fig. 3, the element decomposition includes element disassembly and plane mapping, and the disassembled elements and a plane graph obtained by mapping are combined in a combiner through one or more operations of shape, pattern, color, position, scaling, turning, twisting and array, and then the three-dimensional reconstruction is performed, so that the fusion and recombination of the design elements are realized. The stereo reconstruction refers to a process of remapping the combined graph onto a stereo model according to coordinates in element decomposition. In the preferred scheme, screening is carried out after combination, a plurality of preset rules are set by the set screener, and most of results which do not accord with the design principle are deleted so as to reduce the computation of subsequent stereo reconstruction and the computation of the artificial intelligent model computation step. For example, a blurred image, an image with significant misalignment, and an image with broken patterns are deleted.
The preferred scheme is as shown in FIG. 4, wherein the artificial intelligence model comprises a classifier, a semantic recognizer, an adapter and a clustering device; according to the scheme, the calculation amount of each module can be reduced, the complexity of each module is reduced, and therefore the processing efficiency is improved.
The classifier is used for classifying the three-dimensional model, and the classification is associated with the semantic keywords identified by the semantic identifier; the classifier can reduce the subsequent operation amount. For example, a certain three-dimensional model belongs to summer wear and upper clothes, the color is white, and the fabric is silk without patterns. After classification, adaptation is conveniently carried out according to the requirements of the keywords. The classifier adopts a CNN or fast-CNN deep neural network.
The semantic recognizer is used for converting the input parameters into semantic keywords, and the semantic keywords are associated with the classification of the classifier; namely, the semantic keywords are the basis for classification in the classifier. The semantic recognizer employs RNNs, i.e., recurrent neural networks.
The adapter is used for adapting the sample of the three-dimensional model according to the semantic keywords to adapt the three-dimensional model conforming to the semantic keywords; the adapter can be viewed as a keyword-based filter, with the stereo model data having a keyword hit being able to pass through the adapter and the missing stereo model data being removed by the adapter.
The clustering device is used for aggregating the adapted three-dimensional models according to fashion classification and generating different fashion evaluations. The solution achieves a result that meets the requirements.
In a preferred scheme, the fashion acquisition unit is provided with a three-dimensional model database. The fashion acquisition unit is used for acquiring clothing images of existing popular and classical clothing elements, can acquire the images by using tools such as a crawler and the like on a website to replace time-consuming manual downloading, acquires the elements by using a camera in special places such as a dance hall and certain regions such as Wuhan and Shanghai, and stores the elements in real time by using a data server. In the data server, a standard three-dimensional human body model is stored. Preferably, a typical three-dimensional human body model, such as a child type, a lean type or a fat type, a fat type and other human body models, can be stored, adjustable pieces are arranged on the body surface of the three-dimensional human body model, the clothes are constructed by using the adjustable piece structures, the clothes images of the clothes elements are mapped onto the adjustable piece structures of the clothes according to the acquired positions, and the piece structures are subjected to parameter setting, such as expression of shape, pattern, color, texture and luster. The scheme has the advantages that the finished fashion garment design can directly obtain the model data for cutting, and the model data can be directly applied to different types of corresponding human body models. Greatly reduces the subsequent workload and also has great commercial value.
Example 2:
on the basis of embodiment 1, as shown in fig. 2 to 3, a design method using the fashion design system includes the following steps:
s1, inputting defined parameters including but not limited to body type, skin color, hair style, season, applicable scene and the like, and reading the data of the three-dimensional model by the artificial intelligence model;
as shown in fig. 2, the artificial intelligence model is obtained after artificial labeling, parameter adaptation and model training; through the artificial mark, the artificial intelligence model can obtain comparatively accurate training sample to help the artificial intelligence model to improve the rate of accuracy, because the fashion standard relates to comparatively subjective judgement, consequently the artificial mark plays very important effect in the training process of artificial intelligence model.
The preferred scheme is as shown in FIG. 4, wherein the artificial intelligence model comprises a classifier, a semantic recognizer, an adapter and a clustering device;
the classifier is used for classifying the three-dimensional model according to the keywords; the classifier is used for defining the stereo model in a classified mode, such as corresponding marks for adding body types to the stereo model, applicable seasons, applicable scenes, pattern types, color types, texture types, gloss types, whether elasticity exists or not, specific applicable positions, such as positions of scarves, positions of chestnuts, positions of arm ornaments, positions of waist ornaments and the like, fashion evaluation scores and weighted relation data between the scores and corresponding body types, skin colors and hair styles.
The semantic recognizer is used for converting the input parameters into keywords;
the adapter is used for associating the classified three-dimensional models according to the keywords; and selecting the stereo model according with the input parameters through an adapter.
And the clustering device is used for clustering the correlated three-dimensional models according to fashion evaluation.
In the clustering device, the plane mapping image data of the three-dimensional model is subjected to convolutional coding, the convolutional neural network characteristics of each image are extracted, and the fine-grained classification capability of the algorithm on fashion elements is learned according to a training data set. And a decoder consisting of the convolutional neural network performs clustering operation of the fashion unit, and guides a fashion clothing generation mode according to the training data and the fashion evaluation standard.
S2, carrying out fashion evaluation on the stereoscopic model according to the limited parameters;
in the preferred scheme, the method further comprises the steps of element decomposition and fusion recombination, so that a new sample is generated in the step, one part of the new sample is used for iteration of the artificial intelligence model after artificial marking, parameter adaptation and model training, and the other part of the new sample is sent to the artificial intelligence model for processing;
the element decomposition and fusion recombination steps comprise:
s21, performing element disassembly on design elements, including but not limited to shapes, patterns, colors, relative positions of the patterns and the clothes, materials, textures and gloss;
performing plane mapping on the three-dimensional model; the method includes the steps of expanding a three-dimensional model by a cutting plane to obtain a plane image, and performing subsequent operation by the plane image.
S22, subjecting the disassembled elements to one or more of zooming, turning, twisting, mirroring, sharpening, texturing, blurring and display arrangement or a combined plane structure; the planar structure is a multilayer structure formed by stacking a plurality of planar images, for example, the bottom layer is a planar image of a garment, the upper layer is a pattern, the upper layer is a texture, and the upper layer is an ornament, so that the planar images of the respective layers can be respectively mapped to different structures of a three-dimensional structure.
And S23, carrying out three-dimensional reconstruction on the combined planar structure to realize fusion and recombination.
The adjustable piece structure is arranged on the body surface of the three-dimensional human body model, the adjustable piece structure means that the position and the shape of the piece structure and the connection structure between pieces can be adjusted, the adjustable piece structure is utilized to construct the clothes, the combined plane structure of the clothes image with the clothes elements is mapped to the adjustable piece structure of the clothes according to the collected position, the piece structure is subjected to parameter setting, such as expression of shape, pattern, color, texture and luster, and fusion and recombination operation is realized. And the finished fashion garment design can directly obtain the model data which can be used for cutting.
S3, sending the design with higher fashion ticket evaluation to a fashion generation unit; and the fashion generation unit generates a plane or a three-dimensional graph for display according to the sequence of fashion evaluation, and increases elements for setting off the atmosphere, such as a mannequin, accessories outside the three-dimensional model, atmosphere light, flashing light and shadow and the like in the display process.
Through the steps, fashion design based on artificial intelligence is achieved.
The above-described embodiments are merely preferred embodiments of the present invention, and should not be construed as limiting the present invention, and features in the embodiments and examples in the present application may be arbitrarily combined with each other without conflict. The protection scope of the present invention is defined by the claims, and includes equivalents of technical features of the claims. I.e., equivalent alterations and modifications within the scope hereof, are also intended to be within the scope of the invention.
Claims (10)
1. A fashion design system, characterized by: the fashion acquisition unit, the fashion processing unit, the fashion design unit and the fashion generation unit are included;
the fashion acquisition unit is used for acquiring various fashion elements;
the fashion processing unit is used for counting and learning fashion elements by using a deep learning algorithm;
the fashion design unit is used for separating and reclassifying the clothing attributes representing fashion elements;
the fashion generation unit is used for generating clothes by referring to semantic or environmental conditions.
2. The fashion design system according to claim 1, wherein: the fashion processing unit comprises a training module, wherein a three-dimensional model is built for collected fashion elements in the training module, the three-dimensional model is subjected to artificial marking, the artificial marking model is subjected to parameter adaptation according to input parameters to form a sample set, and the sample set is sent to a deep learning algorithm for training to obtain an artificial intelligent model.
3. The fashion design system according to claim 2, wherein: the fashion design unit comprises an artificial intelligence model for operating the input three-dimensional model and the input parameters, the artificial intelligence model gives fashion evaluation, and data are transmitted to the fashion generation unit.
4. The fashion design system according to claim 2, wherein: the fashion design unit comprises an artificial intelligence model for operating an input three-dimensional model and input parameters, the artificial intelligence model gives fashion evaluation, elements are decomposed, then the elements are fused and recombined, a sample generated after fusion and recombination is divided into two parts, one part is sent into an artificial mark, the artificial mark model is subjected to parameter adaptation according to the input parameters to form a sample set, the sample set is sent into a deep learning algorithm for training, and iteration is carried out on the artificial intelligence model;
and the other part is directly sent into an artificial intelligence model for fashion evaluation.
5. The fashion design system according to claim 4, wherein: the element decomposition comprises element disassembly and plane mapping, the disassembled elements and the mapped plane graph are combined in a combiner through one or more operations of shape, pattern, color, position, zooming, turning, twisting and array, and then three-dimensional reconstruction is carried out, so that the fusion and recombination of the design elements are realized.
6. The fashion design system according to claim 5, wherein: the artificial intelligence model comprises a classifier, a semantic recognizer, an adapter and a clustering device;
the classifier is used for classifying the three-dimensional model, and the classification is associated with the semantic keywords identified by the semantic identifier;
the semantic recognizer is used for converting the input parameters into semantic keywords, and the semantic keywords are associated with the classification of the classifier;
the adapter is used for adapting the sample of the three-dimensional model according to the semantic keywords to adapt the three-dimensional model conforming to the semantic keywords;
the clustering device is used for aggregating the adapted three-dimensional models according to fashion classification and generating fashion evaluation.
7. The fashion design system according to claim 1, wherein: the fashion acquisition unit is provided with a three-dimensional model database.
8. A design method using the fashion design system according to any one of claims 1 to 7, characterized by comprising the steps of:
s1, inputting limiting parameters, and reading the stereo model data by the artificial intelligence model;
the artificial intelligence model is obtained after artificial marking, parameter adaptation and model training;
s2, carrying out fashion evaluation on the stereoscopic model according to the limited parameters;
s3, sending the design with higher fashion ticket evaluation to a fashion generation unit;
through the steps, fashion design based on artificial intelligence is achieved.
9. The fashion design system according to claim 8, wherein:
in step S2, the method further includes the steps of element decomposition, fusion and recombination, so that a new sample is generated, a part of the new sample is used for iteration of the artificial intelligence model after being subjected to artificial labeling, parameter adaptation and model training, and the other part of the new sample is sent to the artificial intelligence model for processing;
the element decomposition and fusion recombination steps comprise:
s21, performing element disassembly on the design elements, wherein the elements comprise shapes, patterns, colors and positions;
performing plane mapping on the three-dimensional model;
s22, subjecting the disassembled elements to one or more of zooming, turning, twisting and displaying or combining a plane structure;
and S23, carrying out three-dimensional reconstruction on the combined planar structure to realize fusion and recombination.
10. The fashion design system according to claim 8, wherein: the artificial intelligence model comprises a classifier, a semantic recognizer, an adapter and a clustering device;
the classifier is used for classifying the three-dimensional model according to the keywords;
the semantic recognizer is used for converting the input parameters into keywords;
the adapter is used for associating the classified three-dimensional models according to the keywords;
and the clustering device is used for clustering the correlated three-dimensional models according to fashion evaluation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111455629.1A CN114357544A (en) | 2021-12-01 | 2021-12-01 | Fashion design system and method for clothes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111455629.1A CN114357544A (en) | 2021-12-01 | 2021-12-01 | Fashion design system and method for clothes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114357544A true CN114357544A (en) | 2022-04-15 |
Family
ID=81098317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111455629.1A Pending CN114357544A (en) | 2021-12-01 | 2021-12-01 | Fashion design system and method for clothes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114357544A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782653A (en) * | 2022-06-23 | 2022-07-22 | 杭州彩连科技有限公司 | Method and system for automatically expanding dress design layout |
-
2021
- 2021-12-01 CN CN202111455629.1A patent/CN114357544A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782653A (en) * | 2022-06-23 | 2022-07-22 | 杭州彩连科技有限公司 | Method and system for automatically expanding dress design layout |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shlyakhter et al. | Reconstructing 3D tree models from instrumented photographs | |
| CN109376582A (en) | A kind of interactive human face cartoon method based on generation confrontation network | |
| Phan et al. | Color orchestra: Ordering color palettes for interpolation and prediction | |
| CN108288072A (en) | A kind of facial expression synthetic method based on generation confrontation network | |
| CN107609193A (en) | The intelligent automatic processing method and system of picture in a kind of suitable commodity details page | |
| CN104981830A (en) | Clothing matching system and method | |
| CN111062260B (en) | Automatic generation method of face-beautifying recommendation scheme | |
| CN110287882A (en) | A kind of big chrysanthemum kind image-recognizing method based on deep learning | |
| CN109993838A (en) | Method and system is sent out in virtual examination based on WebGL and human face rebuilding | |
| CN109961022A (en) | A kind of clothes sketch input fabric material identification analogy method based on deep learning | |
| CN114357544A (en) | Fashion design system and method for clothes | |
| Zhao et al. | Research on the application of computer image processing technology in painting creation | |
| CN112434210A (en) | Clothing fashion trend prediction system and method | |
| CN117333601B (en) | Digital virtual clothing generation method and device based on artificial intelligence | |
| CN115272579A (en) | Single-image three-dimensional garment reconstruction method based on multi-feature fusion | |
| CN110379003A (en) | Three-dimensional head method for reconstructing based on single image | |
| CN109285208A (en) | Virtual role expression cartooning algorithm based on expression dynamic template library | |
| Yan et al. | Mixing and Matching Elements for Intelligent Fashion Design: A Generative Adversarial Network with Structure and Texture Disentanglement | |
| Ravi et al. | Teaching DNNs to design fast fashion | |
| CN116385632A (en) | Intelligent design method for clothing manufacturing enterprises | |
| Podlasov et al. | Japanese street fashion for young people: A multimodal digital humanities approach for identifying sociocultural patterns and trends | |
| CN110461060A (en) | A kind of intelligence landscape system and its working method | |
| Na | Colour image reconstruction in indoor space based on machine vision | |
| CN113869960B (en) | Poster generation method and device, storage medium and computer equipment | |
| CN110399656B (en) | Lower-loading waist-saving parameter design method based on fuzzy logic and neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |