Style compatibility for 3D furniture models

Tianqiang Liu, Aaron Hertzmann, Wilmot Li, Thomas Allen Funkhouser

Research output: Contribution to journalConference articlepeer-review

56 Scopus citations

Abstract

This paper presents a method for learning to predict the stylistic compatibility between 3D furniture models from different object classes: e.g., how well does this chair go with that table? To do this, we collect relative assessments of style compatibility using crowdsourcing. We then compute geometric features for each 3D model and learn a mapping of them into a space where Euclidean distances represent style incompatibility. Motivated by the geometric subtleties of style, we introduce part-aware geometric feature vectors that characterize the shapes of different parts of an object separately. Motivated by the need to compute style compatibility between different object classes, we introduce a method to learn object class-specific mappings from geometric features to a shared feature space. During experiments with these methods, we find that they are effective at predicting style compatibility agreed upon by people. We find in user studies that the learned compatibility metric is useful for novel interactive tools that: 1) retrieve stylistically compatible models for a query, 2) suggest a piece of furniture for an existing scene, and 3) help guide an interactive 3D modeler towards scenes with compatible furniture. Copyright is held by the owner/author(s).

Original languageEnglish (US)
Article number85
JournalACM Transactions on Graphics
Volume34
Issue number4
DOIs
StatePublished - Jul 27 2015
EventACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2015 - Los Angeles, United States
Duration: Aug 9 2015Aug 13 2015

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Keywords

  • Compatibility
  • Crowdsourcing
  • Scene synthesis
  • Style

Fingerprint Dive into the research topics of 'Style compatibility for 3D furniture models'. Together they form a unique fingerprint.

Cite this