Neuromorphic Data Transformations for Sustainable VR Art Applications
Shvets, Anna; Trzepizur, Anthony
Authors
Dr ANNA SHVETS Anna.Shvets@nottingham.ac.uk
ASSISTANT PROFESSOR
Anthony Trzepizur
Abstract
A previously proposed method for adapting 2D digital audiovisual artwork to Virtual Reality (VR) environments utilized time-distributed data (TDD) generators derived from the neuromorphic computing domain. This research advances that approach by emphasizing sustainability, demonstrating improved VR performance and reduced disk space requirements for frames processed through the TDD pipeline compared to raw data. Additionally, we introduce an improved colour palette preservation technique using a mask filtering step, where neuromorphic data serve as a filter for initial colour values. Furthermore, we show that neuromorphic data transformation effectively eliminates noise, providing a viable solution for addressing outliers. The pipeline code and received metrics results are available online: https://github.com/asnota/TDD-method
Citation
Shvets, A., & Trzepizur, A. (2025, June). Neuromorphic Data Transformations for Sustainable VR Art Applications. Paper presented at 10th International XR-Metaverse Conference 2025, Maastricht, Netherlands
