【The creation of digital models should not only serve promotional purposes but also genuinely serve the industry】

A Japanese brand specializing in designing and selling plus-size women’s clothing entrusted us to design and create their exclusive #VhumanIP, because we specialize in creating #DigitalTorso that adapt to body shape data based on different countries, regions, ages, and genders.

We selected digital torso that match the body shapes of the brand’s target consumers for generating the IP, virtual try-ons and showcased style combinations.

(https://lnkd.in/gEaPRjcb

 

https://lnkd.in/gM9-Qwfg)

 

This approach avoids misleading consumers, reduces returns and exchanges, and enhances trust, satisfaction, and mutual benefits.

(https://lnkd.in/gsiP3tup

 

https://lnkd.in/g3DiU-VF)

 

People are increasingly realizing that if virtual try-on displays of digital models only focus on visual aesthetics, it merely fulfills the brand’s style impression and promotion. The true market demand for #VirtualTryon is to achieve both aesthetics and faithfully reproduce the wearing effect in digital displays.

In other words, the creation of digital models should not only serve promotional purposes but also genuinely serve the industry. Because the apparel industry, after all, mostly involves the actual production and sale of products, rather than being purely visual for entertainment purposes.

 

Many sales platforms or self-operated brands think the technical challenge of implementing such a comprehensive virtual try-on daunting simply because they may not fully understand the technological logic and workflow, or they are unaware of companies like ours that provide one-stop services.

【Implement our solution to facilitate the genuine digital transformation of the fashion industry】

        To advance the metaverse fashion business, we must have a clear understanding. There is a fundamental distinction between digital art and digital twin products. The disparity between images and physical products leads to return or exchange requests, and if not addressed, it hinders participant and consumer engagement. Particularly when transitioning from digital to physical production and ultimately delivering to end consumers, the appearance effect alone is insufficient—it must also ensure practical wearability and comfort.

        (https://lnkd.in/gJxzgZ86)

 

        To minimize such return or exchange issues and succeed in creating sellable digital twin products, we assert that the only effective DX solution is one where all data sources start from a 3D state.

 

        While such a DX solution may not yet be offered by providers in other countries, we can provide it through collaboration with our Japan company and affiliated partners.

 

1.AI Fashion

        We possess leading core technology in the creation of digital twin products, although it is not widely known globally due to insufficient promotional efforts.

        (https://lnkd.in/gEh6sbC9)

 

2.Proven in the Chinese Market for 15 Years (Three Areas)

  • Handling variations in body shapes and diverse design requests in ready-to-wear clothing
  • Catering to semi-custom and full-custom orders
  • Providing DX support for creating new brands

        ( https://lnkd.in/gya5MzrE)           

 

3.With consistent technological principles and technical logic, aiming to become a Category Killer across various clothing items in the Asian Market at the very least!

  • Our expertise in MIX&MATCH

        (https://lnkd.in/gvggGZQe)

  • Experience in generating automatic combination tables.

From beautiful “clothes” to beautiful “you”.

  The dress you are wearing is very nice(dress is beautiful).

 

  → The dress suits you very well (you are beautiful).

 Share this transformation with more people.

 

  Create an environment you can easily do clothes shopping anytime, anywhere and no matter whom you are with. And you can receive the object as like as two peas seen in the image.

  Just stop “the picture is only for reference”, we don’t need it any longer.

 

  People all over the world have experienced the same long stay at home because of covid-19. Today’s remote work and 5G environment have achieved so far, and the correspondence of the net sales becomes important in the apparel industry. In the past, you can attract customers attention simply by uploading goods catalog on the Internet. However, nowadays, consumers ask more. Differentiated experience is required to catch their attention and satisfy them. In this digital era, Personal oriented services such as virtual trying on is the best solution.

 

  The purpose of trying on is to satisfy the shopping, so take improving the efficiency of trying on as a service.

(1) Confirmation of size and fit + (2) a good interpretation of you

→ (1) a good interpretation of you ・ confirm the suitable clothes (make a good match just in one step)

  【provide high precision and reliable size and fit clothes】

 

  Instead of just focusing on sales, turn your business to a more sustainable and appreciated mode. A mode in which consumers can design their own clothes and place the order after checking the VR fitting, then the production begins only when receiving an order. Everyone in this business cycle makes contribution to environment protection at the same time.

 

  Sustainability and ethical shopping are familiar words to people now.

People begin to follow the principle in daily life and of course they keep sustainability in mind when they choose clothes.

 

  Deeply loved clothes will be worn more often. Have you ever been hesitated when you want to discard your favorite clothes after wearing it? No matter how expensive the price is, the more times you wear it, in fact, the cost of each time you wear it decreases. The result is also very eco. This awareness is advanced.

Improving this awareness and changing people’s habit is not easy. Let’s start with tiny steps.

 

  As for the mainstream 2D → 3D prototype (virtual garment production) in the apparel industry, I hope we can stop once and think about it.

 

  Why do people have to take fitting in fashion stores? Why is the return rate of online selling clothes so high?

  The answer is often referred to “fit & size” and “plus size”.

 

  If there is no way to solve “fit & size” and “plus size” simultaneously, the high-precision “virtual trying on” service cannot be provided, and the result will inevitably be unable to connect to CX (customer experience).

 

  What I want to draw attention to and emphasize here is that the method can solve “fit & size” and “plus size” simultaneously has already existed. (at least on the upper body)

 

  As a human body, if there is no trunk, arms or legs can’t be existing independently. The essence of the “fit & size” problem is “generation of body trunk garment“, which must be created for covering the body trunk. About 8years ago, our Japanese company has obtained a method to solve the “fit & size” problem, named this as Clone size Ensured Technology (method). Since last year, SdibiT as our joint venture company in China has been kept striving to prove that this method is also applicable to “plus size”.

 

  The decisive difference from the 2D pattern making up to now is the first stage of pattern making for generation of body trunk garment. No matter for which size. [2D pattern making method]and [2D grading method] are not used at all. The prototype of SdibiT is [3D (generate) → 2D → 3D (confirm)], named [Clone Shape Ensured Method] by us because of its extremely high 3D reproducibility of real clothes. That is to say, the comfort and shape of wearing are optimized at the same time, and the 3D virtual garment of the main body has been made in advance. Only by generating 3D virtual garment in advance, can we respond to evolving personalized customization requirement of the market. And it is also an indispensable engineering step to fulfill the personalized customization requirement. It has even been proved that the fine-tuning of higher and more accurate dimensions can be easily achieved by completing this step.

  The foundation of the way of thinking is flattening 3D curved surfaces to 2D.

Reference: https://wiki.mcneel.com/labels/advancedflatting

 

  Watch the animated video of the forepeak tank section of the hull. On the surface of 3D state presentation, where segmentation is needed can be known according to the places where extreme stretching or compression may occur. The degree of compression or stretch is determined by and reflected in the production of high-precision templates. We think this principle is also applicable to the production of 3D virtual garment.

 

  Remember to play “paper craft of regional globe / wallpaper globe” when you were a kid, or football or rugby. To cover the sphere with a lot of small pieces of paper, it is difficult to paste and combine beautifully and accurately in practice. In fact, this is the same as the essence of garment pattern making.

Note 1): the paper globe is equivalent to a 3D virtual garment, not to an avatar or a digital torso(=virtual sewing body).

 

  The garment can be considered as a surface full of curves. The line that divides the garment is the 3Dconstruction line of clothing. By flattening the segmented 3D slices, we can get the best approximate 2D slice plane pattern, which is the entrance to solve the “fit & size” problem. In order to make a difference from the 2D pattern commonly defined so far, we call the small piece of planar pattern (2D) obtained by flattening “2D flatten pattern”.

Note 2): on the 3D virtual garment, it is not just to set the 3D construction line of clothes freely and then generatethe2D flatten pattern. In order to control the tension or compression wrinkling in a certain range, it is necessary to correct the position of the3Dconstruction line of the clothes. The correction of this position will have a great influence on the 3Dreforming of clothes, including the sewing process.

 

Next, the specific examples of fashion design are illustrated.

 

  To make the required 3D virtual garment on an avatar or torso, appropriate loosen setting should be given according to the statistical data or empirical data. The typical examples include air gap thickness.

 

  Appropriate amount of looseness we meant here, can also be some stages or combinations, such as: tight / standard fit / easy fit.

 

  No need to explain that loose quantity is different between men and women’s costume. The difference is also obvious between women’s cheongsam(chi-pao)and shirt blouse.

 

  For example, Chinese cheongsam(chi-pao)is even considered as the second skin layer of women, with little looseness. In order to emphasize the beauty of women’s curve, some ladies pay attention to corrective undergarment or corset to correct their body shape, maintaining the significant S-shaped curve when they stand.

 

  Here we explain simply the influence of different standing posture. When the horizontal cross-section shape of Bust / waist / hip overlaps (cross-section overlaps), you can see the change of the position relationship with Z coordinate. Then the outer circumference of the bust / waist / hip will also change. Even the height of Bust / waist / hip (Y coordinate) varies. That is to say, the posture of standing is different, the shape of avatar is also different. Therefore, it is necessary to think about the posture when wearing the clothes according to different clothing items and give appropriate loosen settings respectively.

 

  It is possible for the instructors (professors, etc.) of college and other educational institutions or brand majors to make a sample garment according to different clothing categories by draping cutting. But it is difficult to keep the same shape if different 3D construction lines are used. In addition, the problem of grading (size expansion) cannot be solved efficiently and accurately in the traditional way, which also troubles many professionals. It is a too much donkeywork to figure out the method, however, that is just the essence of “fit & size” problem.

 

  [example 1] the difference between 2D flatten pattern and 2D pattern in case of two darts being used.

 

  Take women’s shirts which two darts being used for example to demonstrate.

  Suppose you have created the required 3D virtual garment:

 

a) For the 3D virtual garment, follow the steps of 2D pattern making method to set the construction cutting line. First, add a dart from the front armpit to the chest point, then refer to the direction of the usual torso Princess line, and then add another dart at the waist (the second one). Thus, we can see that there are obvious tight stretching or compression parts on 2D flat pattern. (Strong bias area / deformation ratio)

 

b) For the 3D virtual garment, as in a), first add a dart from the front armpit to the chest point. Meanwhile, a 2D flatten pattern is generated, so you can see the place where there is excessive tension, stretching or compression wrinkling. In order to eliminate this kind of excessive scaling, the second dart is added and regenerated into a 2D flatten pattern. Compared with a), it can be found that the small flatten pattern obtained at this time has greatly reduced the expansion strength.

 

  Conclusion: the2D flatten pattern obtained by using the method of B) can be quite close to the 3D virtual garment required. And from the pointof the feasibilityof production and

processing, it is also close to the best data.

  However, just like this, the “fit & size” problem has not been completely solved. As a part of the clothing construction line b), how to decide the position of the second dart, whether it make the part look beautiful (whether it is against the sense of appearance), is still left behind. From the perspective of production and manufacturing, the expansion ofthe2D flatten pattern will not cause problems, and the position of darts should be corrected to a position that can take into account the aesthetic. This is the limit of manufacturing requirement.

  Obtaining the 2D flatten pattern that can match the manufacturing constraints is the way to completely solve the “fit & size” problem.

 

  [example 2] corresponding to personalized customization

 

  13T and 12TL are the ready-to-wear (RTW) sizes of SdibiT and are actually on sale. Here we use the torso of women’s shirt and the bust cross section of 3D virtual garment to demonstrate the description. Here is the actual body shape data of a person (HH) and a 3D virtual garment chest cross section based on personalized customization.

  In daily life, HH is accustomed to wear a bra (push up bra) with lifting effect. Both 13T and 12tl in RTW size can be worn by her in fact. However, HH is not particularly satisfied with neither of the two sizes by trying on comparing.12TL for her, there is not enough space in front and back, and the cup shape of her bra appeared slightly. But 13T for her, loosing on both sides of her left and right armpits, hardly reflects the optimization effect on her body shape brought by the lifting bra. That is to say, the most suitable shirt for her is the shirt (3D shape) with a width of 12TLfrom left to right and a thickness of 13T from front to back, which can make the optimization effect of the bra outstanding. In addition, HH also has her own preference and stress on the cutting line of fabric switching part.

  According to the 3D shape expected by HH, 3D virtual garment is made, and the 3D construction lines that she likes are adopted. Compared with 12TL and 13T, the best position of the garment 3Dconstruction line in the processing restriction range is about 10 mm closer to the front center of the chest cross-section line.

  Referring to the position of 12TLor 13T garment 3Dconstruction line viewed from the front direction, when it is adjusted to the position with beautiful appearance, the combination of three small pieces including the front fly is in the restriction range of subsequent processing. However, there are only two pieces of pattern combination, without the single part of front fly, there will be high possibility of problems in sewing. If the 3Dconstruction line of clothing is within the limit of processing restriction, even without the single part of front fly, there is no problem with only two pieces pattern combination.

  That is to say, for the same 3D garment, the shape and structure of the forepart of the upper body are processed according to the combination of 2 pieces (2 parts) or 3 pieces (3 parts), the position of the 3Dconstruction line of clothing in the production restriction range will be different.

 

  To solve the “fit & size” problem, before 2D → 3D prototype (virtual clothing production), it is necessary to determine the position of 3D construction line of clothing that can take into account both the aesthetic and manufacturing constraints on the basis of 3D virtual garment, and then generate 2D flatten pattern.

————————————————————————————————————————

  In the lectures for instructors (professors, etc.) of collegesand other education professionals, it will be emphasized that:

1.Shape determines position

   ・The 3D virtual garment determines the position of the 3Dconstruction line of clothing within the production restriction limit.

   ・The 3D construction lines of clothes are mutually restricted and influenced

 

2.The position determines the amount of suture ingestion(for ease stitch sewing)

   ・Change the 3Dconstruction line of the clothes, and the amount of contradiction sewing(contraction quantity)required will also change.

 

  Furthermore, in the lectures for employees of clothing enterprises, emphasis follows will be put on:

3.The enterprise should determine the benchmark to maximize the general design

・3D virtual garment should be set as the benchmark, as well as the 3Dconstructionline of clothing that can take into account both aesthetic and limit of production restriction should be determined by the organization that leading the brand operation.

 

Our data assets and data processing workflow are the strong foundation for implementing AI Fashion.

1. The market size and commercial value of AI graphic processing models in the fashion industry.

The global market size of the fashion industry is about $1500 billion per year, while the semiconductor industry has a global market size of approximately $500 billion per year. There is an urgent need for reshaping and tapping into the overlooked immense potential for lucrative opportunities in this untapped blue ocean.

Currently, AI graphic processing technology is widely used in various fields, including computer games, VR, AR, film production, advertising design, medical image processing, and more.

If all of the aforementioned fields involve a connection with garment, then the apparel industry is, in fact, one of the industries with the most extensive application scenarios for AI graphic processing.

However, the digitization level of the fashion industry’s core design and development process, which is the most crucial part of its value chain, lags far behind other industries.

2.  The current status and reasons for the application of AI graphic processing models in the apparel industry.

The application of AIGC in the apparel industry is currently limited to assisting in the design and creative stage.

*AIGC(AI generated content)imagines 

It has not yet empowered the crucial core aspect of this industry. This refers to rapidly converting selected design images into basic pattern graphic data that can be directly used for cutting and sewing.

Furthermore, the clothes created by cutting and sewing according to the converted output of these basic pattern graphic data must ensure that the wearing effect for ordinary consumers faithfully reproduces the effect of the original image. It should not be limited to the tall and slim body proportions of 180cm supermodels, as shown in the picture above.

Currently, people can only obtain approximate design style images through AI-generated graphics. These images do not provide detailed structural line information for each specific body part that can faithfully replicate onto a designated consumer’s body. Garment is three-dimensional and is composed of pieces that are cut, assembled, and sewn together. These individual pieces are patterns which are cut along the structural lines associated with each body part. Detailed information about the construction and shape is required not only for the front view but also for the side and back views.

To recreate the garments depicted in these images, the current process still requires a pattern maker to manually infer and determine the specific cutting and construction lines for the shape and treatment of the front, side, and back views. This is done to ensure that each individual pattern piece can be assembled to create the various forms of clothing, as shown in the picture on the left. Additionally, this process must take into account factors such as the body shape of ordinary consumers and the comfort of wearing the garments. There hasn’t been any change in this process.

  Especially for complex design, pattern makers in the apparel industry often rely on physical draping method. They use cotton grey fabric directly on a physical torso(mannequin) to attempt to recreate the desired image effect. However, this approach relies on closely fitting the fabric to the torso.

  When it comes to actual consumers wearing the garments, achieving the appropriate ease between the clothing and the body becomes a labor-intensive process of repeated adjustments to ensure comfort. It is not as streamlined as our digital design solution (as shown in the image below), which involves accessing a 3D digital torso that can optimize the specified consumer group’s body shape. Based on the digital torso, a garment prototype model is established with the necessary looseness allowance already incorporated for optimal wearing comfort. From there, the garment patterns can be directly cut and unfolded into various shapes, allowing for a one- stop acquisition of patterns that faithfully reproduce the design effect.

 

 

(PS: The hollow space between the 3D digital torso and the outer garment represents the incorporated looseness allowance.)

 

In fact, with the increasingly powerful AI graphics, there is a severe imbalance in work efficiency for pattern makers involved in actual production, leading to growing work pressure.

 

The current principle of AI graphics generation is based on the random combination of prompts. It does not involve on-demand creation based on pre-trained and standardized garment models. The logic behind such random

 

combinations does not allow for the simultaneous generation of 3D garment prototypes with the necessary knowledge of the structure, cutting lines, and shapes of various parts required to recreate the clothing in the image. Furthermore, it is also unable to determine the feasibility of executing such designs in reality unless a variety of garment 3D prototype models are provided to the AI beforehand.

 

To achieve AI automatic pattern-making, there are several prerequisites and steps involved, in addition to the well-known collection and preparation of massive style data, as well as organizing the professional knowledge of production line processes. Among them, the following are crucial:

 

Data annotation: The collected pattern data needs to be annotated, which involves providing key points or bounding blocks for each pattern, enabling the AI to learn the shape and structure of garments.

 

Model training: Utilizing the prepared annotated data, a deep learning model is trained, typically using techniques such as Convolutional Neural Networks (CNN) or Generative Adversarial Networks (GAN), to learn the ability to extract garment shapes and structures from input images.

 

Image processing and feature extraction: The trained model is used to process input images and extract information about the shape and structure of garments. This involves techniques such as image segmentation, key points detection, or bounding block prediction.

 

That is to say, in the fashion industry, there are indeed two important AI graphic processing components: AI Garment Construction, which focuses on automatically recognizing the 3D structure and cutting lines of garments, and AI Generated Content, which involves generating images using AI algorithms.

With AI Garment Construction as the core foundation, which enables the recognition of garment structure and cutting lines, the other AI Generated Content component can use the extracted garment shape and structure information to generate patterns suitable for sewing using graphic processing algorithms. Automatically obtaining patterns becomes a natural outcome.

 

Now, some research institutions and large companies are attempting AI-generated pattern technology, and there has been limited substantial progress despite significant financial investment.

We believe the fundamental reason for this is that the existing pattern graphic data in the field of apparel is mostly created through traditional methods, directly drawn in 2D graphic design software, and measured in centimeters (cm).

However, actual garments are three- dimensional, and the shapes and structural lines presented in their 3D constructed state are often not achievable   through   2D drawings.

The left-right asymmetric design shown in the left images involves continuous and integrated irregular cutting lines. Since these lines are determined  directly  on  a  3D digital

 

prototype model of the garment and unfolded in real-time, they can faithfully conform to consumers of different body types while maintaining a consistent position and presenting a unified appearance.

Attempting to achieve the same result through traditional methods in 2D graphic design software is essentially impossible.

Here’s a simple example as below to illustrate the reason: On a three-dimensional surface, triangular shapes and the positions of their vertices cannot be accurately represented or located using flat drawings. It is not possible to draw triangles with internal angles exceeding 180 degrees or precisely determine the location of vertices through flat drawings.

 

 

Therefore, using traditional 2D drawings to faithfully reproduce 3D garment models does not meet the efficiency and accuracy requirements of the data annotation process necessary for AI-powered automated pattern generation, both in terms of workflow logic and precision.

 

 

3. The data asset advantages of SSFOX (Japan) and SdibiT (China)

SdibiT’s data analysis & processing output technology and know-how originate from SSFOX, our partnership company based in Japan. Over 17 years, we chose the Chinese market as our first target for business expansion because of the fact that China, particularly in women’s fashion, has the largest consumer base in terms of sheer numbers worldwide. Starting our endeavors in China allows us to put our ideas and value proposition into practice. From the perspective of validating and improving our technological services, as well as making genuine efforts towards environmental conservation, this venture holds significant meaning and value.

 

In the era of AI, achieving fully automated pattern-making requires a substantial amount of high-quality data and computational resources for training and processing.

It also necessitates specialized domain knowledge to address the complex challenges of seamless integration between garment design and production line manufacturing.

This includes understanding the basic shape of garments, cutting lines, and assembly methods, among other factors.

 

Generation logic of garment pattern data assets for SSFOX (Japan) and SdibiT (China) follows a 3D → 2D →3D process.

Starting from pre-established 3D prototype models for various garment categories, different structural lines are directly designed on these models. Through algorithms, these lines are then instantly flattened and unfolded into 2D pattern outputs. The resulting graphic data is measured in millimeters (mm) and retains two decimal places. Only with such pattern data can the faithful reproduction of 3D garments be achieved, allowing for on-demand and accurate pattern retrieval.

Here, taking a women’s blouse as an example, as shown in the image below.

The intersection points we annotate on the 3D prototype model of the garment correspond to the same points regardless of the different shapes and patterns generated later on. In other words, the 3D digital garment prototype serves as the “DNA” of our digital design and pattern-making solution. Just like human genes, even though the final appearance may vary greatly after evolution, since it is DNA, tracing and verifying it will always lead back to the corresponding original point, as the example shown in the image below.

This is of significant importance in the data annotation phase, which is an indispensable part of the AI learning process. It ensures consistency and accuracy throughout the pattern-making process, allowing AI algorithms to learn and adapt based on the annotated data.

This technological workflow allows our garment pattern data assets to possess the following characteristics:

 

High Quality and Precision: The pattern graphic data is measured in millimeters with two decimal places, providing more accurate measurements and richer detail information. Training AI models with high-quality pattern graphic data enhances the accuracy and reliability of the AI-generated patterns.

 

Facilitates Free Exchange and Combination: Traditional 2D drawing software cannot achieve the flexibility of combining pattern pieces like our pattern graphic data does. The ability to flexibly combine pattern pieces enables the creation of different designs and styles (we call it the magic of mix&match). This flexibility and combinability, when harnessed by AI’s discriminative combination, can lead to exponential growth in disruptive design innovation.

 

Historically Validated and Practically Applied:The pattern graphic data has undergone over 10 years of practical sewing production validation. It can be used to cut and sew garments with different designs through free exchange and combination. This flexibility allows for quickly meeting customers’ personalized demands during the sales process. Our physical stores in Wuxi, China, have gained popularity. Through these experiences, we have developed rich and unique know-how in assessing the feasibility of pattern data in real production lines.


Scarcity and Uniqueness:Pattern graphic data that simultaneously meets the above three characteristics is scarce and unique in the market. Other companies or organizations would find it challenging to obtain or replicate similar data.

There is a growing demand in the market for automated pattern generation. However, pattern data that can accurately reproduce design concepts, particularly those with proven supply, is scarce. Our next goal is to make more industry enterprises and organizations aware that our data assets can meet these demands and be applied in relevant industries.

 

Business promotion strategies

 

We aim to cater to institutions and companies engaged in the research and development of AI automated pattern-making technology by providing a substantial amount of high-quality training data that meets their specific data requirements and conditions.

This includes optimizing digital body models for specific demographics, digital garment prototype models for various garment categories, and an extensive collection of pattern data that can be directly derived from 3D garment prototype models. This pattern data exhibits various shapes and fulfills the criteria for free exchange and combination.

 

Some research institutions and companies have invested heavily in developing technology for automated pattern generation. Here are some well-known institutions and companies we are aware of:

  OpenAI : Their researchers have been exploring the application of computer vision and generative models in the field of fashion design, including automated pattern generation technology.

  Adobe : A renowned creative software company, Adobe has been developing AI and computer vision-based creative tools. Their research team is investigating automated pattern generation technology to simplify the process of fashion design and manufacturing.

  Stitch Fix: A personalized fashion subscription service company, Stitch Fix utilizes machine learning and AI to recommend clothing styles to users. Their research team has been studying how to use AI technology to generate personalized patterns to better meet user needs.

  Loom.ai : A company specializing in virtual reality and augmented reality technology, Loom.ai’s researchers are exploring the use of machine learning and computer vision to automatically generate virtual garment patterns, enhancing the virtual reality experience.

 

 

(The information provided above is based on our knowledge and may not represent the most current developments in these companies’ research activities.)

【We are here!】

For the first time, we are integrating home textile products with daily clothig, utilizing end-to-end digital technology support from design to production line data conversion which can be restored 1:1, and product digital showcasing.

At the 134th China Import & Export Fair from October 31st to November 4th, we will be located at booth 9.2B05.
Our clients, who benefit from our technical services as effective users, will demonstrate on-site what “win-win” truly means.

【What is AI’s view on the issue of the AI application in directly converting clothing designs into production patterns?】

We have held the 3D digital fashion design & pattern-making workshop regularly for three years. This year, for the first time, all five participants have a master’s degree or higher, with one participant holding a Ph.D.

During the first day’s discussion, one of them brought up the idea of hearing AI’s opinion to verify the perspective and method I presented.
It seems that AI agrees with me as the attached screenshot photos❗ Ha-ha…
The text also highlights in blue that “This is a complex task that requires a deep understanding of garment construction and patternmaking principles” – which suggests that AI recognizes the importance of having a strong foundation in the principles of garment construction and patternmaking to successfully carry out the proposed approach.

In fact, even before the emergence of powerful AI drawing tools like today, we have been offering consumers a whole solution to customization haute couture as following.
Without AI drawing tools, consumers can use our relatively sophisticated models for simple customization and creation, and choose from designs to create their own unique clothing.
For more than a decade, we collected fashion design data from fashion shows published in Vogue by top brands. And these data work as AI drawing tools.
We select the design suits actual target consumers from abundant pictures and integrate various construction lines‘ essence.
And the method used throughout is to design directly on the 3D digital garment model made from the 3D digital torso and output 2D patterns in real time.

https://lnkd.in/gywZcCh8
https://lnkd.in/gSJznKUa


We are also proud that SSFOX/SdibiT is the only private company that has been featured by the famous economic program #WBS(“world business satellite” )of #TVTokyo as an international digital fashion pioneer.

31st May, 2023

【Will the AI refuse to accept pattern data generated in 2D CAD drawing software for further processing?】

Generative AI is a hot topic of the moment, and we all know that everything AI can do requires a process of learning from the data we provided.

Let’s start to think about AI application in clothing pattern generation, and we will realize a very serious and logically important issue.

The ultimate forms of both virtual clothing and physical clothing are 3D. And the common source is clothing pattern data.
If the pattern data provided for AI learning is generated from 2D CAD drawing software, then the source data is not generated in 3D state, it is not logical that AIGC can play a role in this situation.
All kinds of existing picture generation, can only be skin, and can not achieve the real meaning of DX❗️

2D and 3D are completely different dimensions, so no matter how AI learns, it can not make perfect transformation.
AI need to learn that a combination of 2D patterns can be generated with different shapes based on cutting lines on the same 3D garment model.

If there were no massive pattern data generated like our method to provide for AI learning, there would never have been an AI product that could directly restore and convert a picture of a garment worn on people into pattern sets that could be produced automatically or semi-automatically❗

https://lnkd.in/gprpAubA
https://lnkd.in/gvggGZQe
https://lnkd.in/gTufNWJ9

According to the content of an interview with Professor Geoffrey Hinton at MIT Technology Review on May 3, soon AI will be able to conduct thought experiments.
Will the AI refuse to accept pattern data generated in 2D CAD drawing software for further processing❓🧐🧐

21st May,2023
#design #digital #digitalfashion #digitaltwin #3dmodeling #sustainability #apparelindustry #metaverse #fashiondesign #AIinfashion #AIGC #business