Year: 2004
Type: article
Abstract: A major drawback of shopping for clothes on-line is that the customer cannot try on clothes and see if they fit or\nsuit them. One solution is to display clothing on an avatar, a 3D graphical model of the customer. However the\nnormal technique for modeling clothing in computer graphics, cloth dynamics, suffers from being too processor\nintensive and is not practical for real time applications. Hence, retailers normally rely on a fixed set of body\nmodels to which clothes are pre-fitted. As the customer has to choose from this limited set the fit is typicallly not\nvery representative of how the real clothes will fit. We propose a method that uses a compromise between these\ntwo methods. We generate a set of example avatars by performing Principal Component Analysis on a dataset of\navatars. Clothes are pre-fitted to these examples off-line. Instead of asking the customer to choose from the set of\nexamples we are able to represent the users avatar as a weighted sum of the examples, we then fit clothes as the\nsame weighted sum over the clothes fitted to the examples.
Institutions: University College London, Hungarian Academy of Sciences
Language: English
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2150121711