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]

Preview	Text 08_Lomas_EVA22.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview
	Text EVA2022_SynthesisUsingSirens_paper_003.pdf - Accepted Version Permissions: Administrator Access Only Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (823kB)

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)
Identification Number (DOI):	https://doi.org/10.14236/ewic/EVA2022.2
Related URLs:	http://www.eva-london.org/eva-london-202...
Departments, Centres and Research Units:	Computing
Dates:	Date Event 5 February 2022 Accepted July 2022 Published
Event Location:	London, United Kingdom
Date range:	4-8 July 2022
Item ID:	31491
Date Deposited:	21 Feb 2022 16:14
Last Modified:	30 Mar 2023 14:26
URI:	https://research.gold.ac.uk/id/eprint/31491

View statistics for this item...

Edit Record (login required)