Toward Computer Aided Visual Analogy Support (CAVAS): Augment Designers Through Deep Learning

Abstract

The goal of this research is to develop a computer-aided visual analogy support (CAVAS) framework that can augment designers’ visual analogical thinking by providing relevant visual cues or sketches from a variety of categories and stimulating the designer to make more and better visual analogies at the ideation stage of design. The challenges of this research include what roles a computer tool should play in facilitating visual analogy of designers, what the relevant and meaningful visual analogies are at the sketching stage of design, and how the computer can capture such meaningful visual knowledge from various categories through analyzing the sketches drawn by the designers. A visual analogy support framework and a deep clustering model, called Cavas-DL, are proposed to learn a latent space of sketches that can reveal the shape patterns for multiple categories of sketches and at the same time cluster the sketches to preserve and provide category information as part of visual cues. The latent space learned serves as a visual information representation that captures the learned shape features from multiple sketch categories. The distance- and overlap-based similarities are introduced and analyzed to identify long- and short-distance analogies. Extensive evaluations of the performance of our proposed methods are carried out with different configurations, and the visual presentations of the potential analogical cues are explored. The evaluation results and the visual organizations of information have demonstrated the potential of the usefulness of the Cavas-DL model.