Fashion is Taking Shape: Understanding Clothing Preference Based on Body Shape From Online Sources

Hosnieh SattarGerard Pons-MollMario Fritz
Scalable Learning and Perception Group, Real Virtual Humans
Max Planck Institute for Informatics, Saarbrucken, Germany
 

Abstract

To study the correlation between clothing garments and body shape, we collected a new dataset (Fashion Takes Shape), which includes images of users with clothing category annotations. We employ our multi-photo approach to estimate body shapes of each user and build a conditional model of clothing categories given body-shape. We  demonstrate that in real-world data, clothing categories and body-shapes are correlated and show that our multi-photo approach leads to a better predictive model for clothing categories compared to models based on single-view shape estimates or manually annotated body types. We see our method as the first step towards the large-scale understanding of clothing preferences from body shape.

 

 

Fashion Takes Shape Dataset

Not every clothing item matches every body shape. Hence our goal is to study the link between body shapes and clothing categories. In order to study these correlations, we collected data from 181 users of ``Chictopia''(http://www.chictopia.com,online fashion blog).

We look for two sets of users: in the first set, we collected data of users with average and below the average size, which we call group Ga; the second set contains data of plus size and above average users referred to as Gp. In total, we have 141 users in group Ga and 40 in group Gp which constitute a diverse sample of real-world body shapes. Figure1, shows the summary of our data set. The total number of posts from all users is 18413 -- each post can contains one or more images (usually between 2 to 4). The minimum number of posts per user is 1 and the maximum 1507. In average, we have 102 posts per user, and a median of 38 posts per user. Furthermore, each post contains data about clothing garments, other users opinions (Votes, likes) and comments. Figure2, shows a post uploaded by a user, and Figure3 shows several samples from the dataset.

 

Paper on arXiv

Citation:

@online{Sattar,
  author = {Hosnieh Sattar, Gerard Pons-Moll, Mario Fritz},
  title = {Fashion is Taking Shape: Understanding Clothing Preference Based on Body Shape From Online Sources},
  url = {http://arxiv.org/abs/1807.03235},
  eprint = {1807.03235},
  eprinttype = {arXiv},
  year = {2018},
}