Studio2Shop: from studio photo shoots to fashion articles
This addresses the street-to-shop task for fashion search, helping shoppers find clothing items from studio photos, but it is incremental as it builds on existing domain-specific representations.
The paper tackles the problem of matching studio photos of people wearing clothing to shop images of the same fashion items, achieving top-k retrieval performance that is sufficient for building realistic visual search engines in the studio-to-shop setting.
Fashion is an increasingly important topic in computer vision, in particular the so-called street-to-shop task of matching street images with shop images containing similar fashion items. Solving this problem promises new means of making fashion searchable and helping shoppers find the articles they are looking for. This paper focuses on finding pieces of clothing worn by a person in full-body or half-body images with neutral backgrounds. Such images are ubiquitous on the web and in fashion blogs, and are typically studio photos, we refer to this setting as studio-to-shop. Recent advances in computational fashion include the development of domain-specific numerical representations. Our model Studio2Shop builds on top of such representations and uses a deep convolutional network trained to match a query image to the numerical feature vectors of all the articles annotated in this image. Top-$k$ retrieval evaluation on test query images shows that the correct items are most often found within a range that is sufficiently small for building realistic visual search engines for the studio-to-shop setting.