When high technology is not attempting to save the world from its real (and imaginary) ills, it’s nice to know it dips into some of the more important aspects of life, like shopping for clothes that fit well. Never has that aspect of life been more important than now, when shopping for clothes online does not afford one the opportunity to try garments on before purchasing. Well, let not your heart be troubled, the folks at the Hong Kong Polytechnic University (PolyU) may have just the solution for this pressing dilemma.
Intelligent 3D human modelling technology, developed by researchers at the Hong Kong Polytechnic University (PolyU), digitally reconstructs the shape and size of a person accurately from two full body photographs within 5s to10s. The PolyU innovation was developed by Dr Tracy P.Y. Mok, Associate Professor from the Institute of Textiles and Clothing at PolyU, and Dr Zhu Shuaiyin, PhD graduate of the same institute. They claim their paradigm can solve the ill-fitting problem and enhance the online shopping experience.
According to the researchers, existing methods to achieve automatic shape modeling involve expensive and bulky scanners and much approximation, which yields questionable accuracy.
Using computer graphic and vision technology, the PlyU system creates a customized model in arbitrary dynamic poses within 5s to10s. It can reconstruct the 3D shape and extract over 50 accurate size measurements of different parts of a person, including girth of the bust, waist, hip, thigh, knee, calf, and neck, as well as arm length and shoulder slope. The discrepancies in tight-fitting and loose-fitting clothing are less than 1cm and 2cm respectively, which may be enough to fulfil the specific requirements of the clothing industry for fashion applications.
Four methods realize automatic shape modelling of individuals by:
- 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 in arbitrary clothing, including tight-fitting, normal-fitting and loose-fitting clothing.
- applying cutting-edge deep learning technology to segmentize the human body image from the background. It also improves the robustness, efficiency and accuracy of shape modelling of individuals.
- applying the above modelling methods to develop a client-server system. It is a mobile application (available on iTunes and Google Play) of the automatic shape customization technology, starting from photo taking to model customization and size extraction.
These methods are enabled by big-data analytics, where a dataset with over 10,000 human scan models were used to analyze local 3D shape features and predict under-the-clothes body profiles. Different from other existing methods where 3D scans are analyzed globally, PolyU’s research team decomposes the data yielded from 3D scans into local features for data analysis. The team then predicts and assembles the 2D and 3D shapes of subjects based on 2D photographs. The resulting 3D models have precisely reconstructed both global and local shape characteristics of individuals, and accurate body measurements can be extracted from these customized models.
Commercialization
With the support from Shanghai Technology Entrepreneurship Foundation-PolyU China Entrepreneurship Fund, Dr Zhu has created the start-up, TOZI, in Shenzhen in 2017 to commercialize and further develop the 3D human modelling technology, echoing PolyU’s commitment to foster culture that boosts entrepreneurship and inspires entrepreneurs. Hey, what good is art or technology if you can’t sell it? Hopefully, tariffs won’t fluctuate.
If high fashion technology is your passion, checkout a mobile-app demo video and a video of the service launched by TOZI. For more details, you can contact Dr. Tracy P.Y. Mok via email at [email protected] and/or Dr. Zhu Shuaiyin at [email protected].