Learning Style Compatibility for Furniture

Divyansh Aggarwal, Elchin Valiyev, Fadime Sener und Angela Yao
In: German Conference on Pattern Recognition (2018)(552-566)
 

Abstract

When judging style, a key question that often arises is whether or not a pair of objects are compatible with each other. In this paper we investigate how Siamese networks can be used efficiently for assessing the style compatibility between images of furniture items. We show that the middle layers of pretrained CNNs can capture essential information about furniture style, which allows for efficient applications of such networks for this task. We also use a joint image-text embedding method that allows for the querying of stylistically compatible furniture items, along with additional attribute constraints based on text. To evaluate our methods, we collect and present a large scale dataset of images of furniture of different style categories accompanied by text attributes.

Bonn Furniture Styles Dataset

Bilder

Paper herunterladen

Paper herunterladen

Zusätzliches Material

Bibtex

@ARTICLE{aggarwal2018learning,
    author = {Aggarwal, Divyansh and Valiyev, Elchin and Sener, Fadime and Yao, Angela},
     pages = {552--566},
     title = {Learning Style Compatibility for Furniture},
   journal = {German Conference on Pattern Recognition},
      year = {2018},
  abstract = {When judging style, a key question that often arises is whether or not a pair of objects are
              compatible with each other. In this paper we investigate how Siamese networks can be used
              efficiently for assessing the style compatibility between images of furniture items. We show that
              the middle layers of pretrained CNNs can capture essential information about furniture style, which
              allows for efficient applications of such networks for this task. We also use a joint image-text
              embedding method that allows for the querying of stylistically compatible furniture items, along
              with additional attribute constraints based on text. To evaluate our methods, we collect and present
              a large scale dataset of images of furniture of different style categories accompanied by text
              attributes.}
}