Princeton > CS Dept > PIXL > Graphics > Publications Local Access 

Style Compatibility for 3D Furniture Models
ACM Transactions on Graphics (Proc. SIGGRAPH), August 2015

Tianqiang Liu, Aaron Hertzmann, Wilmot Li,
Thomas Funkhouser


This paper proposes a method to learn a metric for stylistic compatibility between furniture in a scene. (a) The image on the left shows a plausible furniture arrangement, but with a randomly chosen mix of clashing furniture styles. The scene on the right has the same arrangment but with furniture pieces chosen to optimize stylistic compatibility according to our metric.

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.

Citation (BibTeX)

Tianqiang Liu, Aaron Hertzmann, Wilmot Li, and Thomas Funkhouser. Style Compatibility for 3D Furniture Models. ACM Transactions on Graphics (Proc. SIGGRAPH) 34(4), August 2015.

Paper
  6.6M

Links
  Code and data
  Supplemental material
  Video

Talk
  PDF
  PPTX