Improving Style Similarity Metrics of 3D Shapes

TL;DR

This paper enhances 3D shape style similarity metrics by incorporating color and texture, exploring clustering effects, enabling user-guided learning, and proposing an iterative learning approach for diverse models, improving style-based applications.

Contribution

It introduces four novel improvements to 3D shape style similarity metrics, including color/texture consideration, clustering effects, user-guided learning, and an iterative learning method.

Findings

Improved style similarity metrics with color and texture inclusion.

Clustering influences on style metric effectiveness.

Effective user-guided and iterative learning approaches.

Abstract

The idea of style similarity metrics has been recently developed for various media types such as 2D clip art and 3D shapes. We explore this style metric problem and improve existing style similarity metrics of 3D shapes in four novel ways. First, we consider the color and texture of 3D shapes which are important properties that have not been previously considered. Second, we explore the effect of clustering a dataset of 3D models by comparing between style metrics for a single object type and style metrics that combine clusters of object types. Third, we explore the idea of user-guided learning for this problem. Fourth, we introduce an iterative approach that can learn a metric from a general set of 3D models. We demonstrate these contributions with various classes of 3D shapes and with applications such as style-based similarity search and scene composition.