Exploring the Perceived Complexity of 3d Shapes: Towards a Spatial Visualization VR Application

Abstract

The objective of this work is to explore the perceived complexity of 3D shapes used in spatial visualization tasks and leverage Machine Learning to create a model that can predictthis perceived complexity using the visual features of the shapes. This could help automate the process of generating 3D shapes for a Virtual Reality (VR) application designed to help develop spatial visualization skills. Spatial visualization skills are important skills needed in the STEM fields. While VR has been used to help develop these skills, most of the existing applications do not necessarily tailor their content to the skills level of individuals. Automatically generating shapes can help VR applications tailor spatial visualization tasks to the skills level of users. However, in order to do this, it is important to first understand how humans perceive the complexity of 3D shapes, and how this relates to their performance in spatial visualization tasks. The results of this work indicate that while participants perceived complexity of 3D shapes is correlated to their performance in spatial visualization tasks that use the same 3D shapes, this perceived complexity by itself is not enough to predict their performance in such tasks. Moreover, the results indicate that certain visual features of 3D shapes can help explain the perceived complexity of the shape as well as the performance of individuals in spatial visualization tasks that implement those 3D shapes.