본문 바로가기
  • Home

Particle-Aware Velocity–Density Sound Mapping

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2026, 31(5), pp.105~113
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : February 23, 2026
  • Accepted : March 30, 2026
  • Published : May 29, 2026

Jong-Hyun Kim 1

1인하대학교

Accredited

ABSTRACT

This paper proposes a data-driven sound synthesis framework that generates synchronized audio from foam particle dynamics in 3D motion videos. Energy and density descriptors derived from particle motion are mapped to audio selection, volume, and filtering. Dynamic K-means clustering and candidate reduction improve efficiency and variation, while multi-frame synthesis with cross-fading and filtering ensures temporal continuity. Experiments show responsive and coherent audio aligned with particle changes, demonstrating an interpretable approach extendable to other particle-based phenomena and learning-based models.

Citation status

* References for papers published after 2024 are currently being built.

This paper was written with support from the National Research Foundation of Korea.