Home // ACHI 2026, The Nineteenth International Conference on Advances in Computer-Human Interactions // View article

Dynamic Diorama: Narrative-Driven Orientation Modeling and Object Placement for VR

Authors:
Furkan Çelen
Meral Kuyucu
Bora Şenceylan
Gökhan İnce

Keywords: narrative-driven scene generation; VR storytelling; semantic layout reasoning; spatial placement.

Abstract:
Spatial composition is a key factor in Virtual Reality storytelling, as object arrangement directly influences how users perceive meaning and emotion. However, converting text into 3D layouts is difficult because systems typically prioritize geometric rules over narrative context. Dynamic Diorama moves beyond simple geometry by analyzing text for structural details and emotional cues to shape the layout. Rather than just placing objects randomly or by rigid rules, our pipeline aligns the spatial relationships directly with the story’s mood. This approach is benchmarked against standard baselines across four distinct narrative themes: happiness, fear, surprise, and sadness. Participant feedback indicated that the Large Language Model driven scenes offered significantly better narrative coherence and emotional alignment compared to the random and heuristic baselines. Eye-tracking data supported this finding, revealing that semantically informed scenes reduced the time-to-first-fixation on key narrative elements.

Pages: 95 to 101

Copyright: Copyright (c) IARIA, 2026

Publication date: May 24, 2026

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-68558-383-5

Location: Venice, Italy

Dates: from May 24, 2026 to May 28, 2026