Patternista: Learning Element Style Compatibility and Spatial Composition for Ring-based Layout Decoration

Abstract

Creating aesthetically pleasing decorations for daily objects is a task that requires deep understanding of multiple aspects of object decoration, including color, composition and element compatibility. A designer needs a unique aesthetic style to create artworks that stand out. Although specific subproblems have been studied before, the overall problem of design recommendation and synthesis is still relatively unexplored. In this paper, we propose a flexible data-driven framework to jointly consider two aspects of this design problem: style compatibility and spatial composition. We introduce a ring-based layout model capable of capturing decorative compositions for objects like plates, vases and pots. Our layout representation allows the use of the hidden Markov models (HMM's) technique to make intelligent design suggestions for each region of a target object in a sequential fashion. We conducted both quantitative and qualitative experiments to evaluate the framework and obtained favorable results.