Synthesis of Abstract Dynamic Quasiperiodic 3D Forms using SIRENs

Lomas, Andy. 2022. 'Synthesis of Abstract Dynamic Quasiperiodic 3D Forms using SIRENs'. In: EVA London 2022. London, United Kingdom 4-8 July 2022. [Conference or Workshop Item] (In Press)

EVA2022_SynthesisUsingSirens_paper_003.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (823kB) | Preview

Abstract or Description

This paper explores using SIRENs, neural networks with periodic activation functions, as a means for synthesising abstract three-dimensional dynamic forms. A SIREN is used to generate a field function for an implicit surface, with inputs for 3D position and time. A wide range of complex quasiperiodic forms can be created, with synthesis and rendering being achievable at interactive rates using modern graphics hardware.

Item Type:

Conference or Workshop Item (Paper)

Related URLs:

Departments, Centres and Research Units:



5 February 2022Accepted

Event Location:

London, United Kingdom

Date range:

4-8 July 2022

Item ID:


Date Deposited:

21 Feb 2022 16:14

Last Modified:

21 Feb 2022 17:01


View statistics for this item...

Edit Record Edit Record (login required)