PetGen: Design and Generation of Virtual Pets

Virtual pets are essential virtual characters in-game narratives and can influence players' sense of immersion. However, the design of virtual pets' appearances is often repetitive work that relies on the designers' experiences without association with the pets' potential personalities. In this work, we propose PetGen, an application that can generate varying virtual pets' appearances following the Five-Factor Model (FFM) based on AI algorithms. The 3D voxel virtual pets' appearances were initialized under four initial archetypes and then underwent recombination, dyeing, and texturing stages, where AI algorithms were applied as filters. We conducted a pilot study to learn users' perceptions of machine-generated pets. The findings revealed that participants preferred the generated pets more than those manually designed. In future work, we will explore other machine learning approaches for 3D voxel object generation, especially virtual pets with more diverse personalities and appearance traits.