Home / Knowledge / News / Apparel/Garments / Hong Kong's PolyU tech projects body shape, size in 10 Sec
Hong Kong's PolyU tech projects body shape, size in 10 Sec
09
May '18
The Hong Kong Polytechnic University (PolyU) has developed an intelligent 3D human modelling system by integrating computer graphic and vision technology to simplify and enhance the process of shopping well-fitting clothes online. The system digitally accurately reconstructs the shape and size of a person from two full body photographs within 5-10 seconds.

Developed by Tracy P.Y. Mok, associate professor from PolyU’s Institute of Textiles and Clothing and PhD graduate Zhu Shuaiyin, the innovation allows a customised model in arbitrary dynamic poses to be created automatically within 5-10 seconds, according to a press release from Zhu’s start-up TOZI.

Existing methods to achieve automatic shape modeling and dynamic poses deformation, including scan-based, image-based and example-based have known limitations. They involve expensive and bulky scanners and too much approximation, and therefore are of questionable accuracy.

The system can reconstruct the 3D shape and extract over 50 size measurements of different parts of a person, including the girth of bust, waist, hip, thigh, knee, calf and neck, as well as arm length, shoulder slope accurately. The discrepancies in tight-fitting and loose-fitting clothing are less than 1cm and 2cm respectively, which are precise enough to fulfil the specific requirements of the clothing industry for fashion applications and comparable to body scans.

Four methods were used to digitise human models: detecting body parts in tight fitting clothing from front-view and side-view 2D images and then construct them to 3D models; predicting under-the-clothes body profiles of the subjects based on input images where the body profiles are covered; applying cutting-edge deep learning technology to segmentise the human body image from the background; and applying the modelling methods to develop a client-server system.

These methods are enabled by big data analytics, where a large dataset with over 10,000 human scan models were used to analyse local 3D shape features and predict under-the-clothes body profiles.

With the support from Shanghai Technology Entrepreneurship Foundation-PolyU China Entrepreneurship Fund, Zhu set up TOZI in Shenzhen in 2017 to commercialise and further develop the technology. (DS)

Fibre2Fashion News Desk – India


Must ReadView All

Possible changes to US-Korea FTA origin rules to be probed

Apparel/Garments | On 20th Mar 2019

Possible changes to US-Korea FTA origin rules to be probed

The US International Trade Commission is seeking inputs on a new...

Uzbekistan, UAE explore partnership in trade, investment

Textiles | On 20th Mar 2019

Uzbekistan, UAE explore partnership in trade, investment

Uzbekistan and the United Arab Emirates (UAE) have agreed to increase ...

Pic: Infor

Textiles | On 20th Mar 2019

ERP's future is network-centric, cloud-based: Infor

While traditional enterprise resource planning (ERP) was enterprise...

Interviews View All

Saket Garg, Garg Corporation

Saket Garg
Garg Corporation

The biggest challenge is lack of skilled workforce and competition from...

Karel Williams, Dow Microbial Control

Karel Williams
Dow Microbial Control

'Silvadur is most rapidly adopted in areas where hygiene-conscious and...

Anavila Misra, Anavila Collection

Anavila Misra
Anavila Collection

Fashion shows are also encouraging and highlighting sustainable fashion

Kamal Kulshreshth,

Kamal Kulshreshth

Colorjet is among the fastest-growing wide format digital inkjet print...

Tejas N Patel, Navin D Patel,

Tejas N Patel, Navin D Patel

Founded in 1999 by Navin Patel in the name of Tejas Fabrics with 100...

Larry Fontana,

Larry Fontana

Italy-based Lafer SpA is one of the most innovative surface finishing...

Razvan Popescu, Directa Plus SpA

Razvan Popescu
Directa Plus SpA

Directa Plus is one of the largest producers and suppliers worldwide of...

Larry L Kinn, Suominen Corporation

Larry L Kinn
Suominen Corporation

Larry L Kinn, Senior Vice President - Operations Americas of Suominen...

Davide Vigano, Sensoria

Davide Vigano
Sensoria

Sensoria is a leading developer of smart garments and IoMe (Internet of...

Adriano Goldschmied, AG Jeans

Adriano Goldschmied
AG Jeans

The hype around 'designer jeans' was created by him. And the new wave of...

Sanjukta Dutta, Sanjukta's Studio

Sanjukta Dutta
Sanjukta's Studio

<b>Sanjukta Dutta</b> creates unique garments by clubbing prints of...

Hemant & Nandita, Hemant & Nandita

Hemant & Nandita
Hemant & Nandita

The designer duo of Hemant &amp; Nandita are known for being inspired by...

Press Release

Press Release

Letter to Editor

Letter to Editor

RSS Feed

RSS Feed

Submit your press release on


editorial@fibre2fashion.com

Letter To Editor






(Max. 8000 char.)

Search Companies





SEARCH

Leave your Comments


March 2019

Subscribe today and get the latest update on Textiles, Fashion, Apparel and so on.

news category


Related Categories:

Advanced Search