Collaborative Evolution of 3D Models

TL;DR

This paper introduces a collaborative interactive genetic algorithm system for 3D model design, enabling designers to share solutions and explore creative transformations collectively, resulting in comparable creativity levels but different design outcomes.

Contribution

It presents a novel collaborative IGA framework that incorporates solution sharing among designers, expanding the search space for creative 3D modeling.

Findings

Collaborative models are rated equally creative as individual models.

Sharing solutions alters the resulting designs significantly.

The approach facilitates quick exploration of design variations.

Abstract

We present a computational model of creative design based on collaborative interactive genetic algorithms. In our model, designers individually guide interactive genetic algorithms (IGAs) to generate and explore potential design solutions quickly. Collaboration is supported by allowing designers to share solutions amongst each other while using IGAs, with the sharing of solutions adding variables to the search space. We present experiments on 3D modeling as a case study, with designers creating model transformations individually and collaboratively. The transformations were evaluated by participants in surveys and results show that individual and collaborative models were considered equally creative. However, the use of our collaborative IGAs model materially changes resulting designs compared to individual IGAs.