Towards Crowd-Sourced Parameter Optimisation for Procedural Animation

Henshall, Gareth I.; Headleand, Christopher J.; Teahan, William J.; Cenydd, Llyr ap

doi:10.1109/cw.2015.57

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have previously conducted a similar experiment to the one described in this paper on a much simpler procedural animation system, consisting of seven parameters describing basic snake-like creatures [31,32]. In that experiment, we asked participants to rate randomly generated creatures on their physical attributes.…”

Section: A Dolphin Modelmentioning

confidence: 99%

Virtual reality’s effect on parameter optimisation for crowd-sourced procedural animation

2018

Self Cite

View full text Add to dashboard Cite

Procedural animation systems are capable of synthesising lifelike organic motion automatically. However, due to extensive parameterisation, tuning these systems can be very difficult. Not only are there potentially hundreds of interlinked parameters, the resultant animation can be very subjective and the process is difficult to automate effectively. In this paper, we describe a crowd-sourced approach to procedural animation parameter optimisation using genetic algorithms. We test our approach by asking users to interactively rate a population of virtual dolphins to a prescribed behavioural criterion. Our results show that within a few generations a group of users can successfully tune the system towards a desired behaviour. Our secondary motivation is to investigate whether there are differences in animation and behavioural preference between observations made using a standard desktop monitor and those made in virtual reality (VR). We describe a study where users tuned two sets of dolphin animation systems in parallel, one using a normal monitor and another using an Oculus Rift. Our results indicate that being immersed in VR leads to some key differences in preferred behaviour.

show abstract

Section: A Dolphin Modelmentioning

confidence: 99%