Adaptive virtual reality system remembers user layout preferences
SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL
Artificial IntelligenceHuman-Computer Interaction
Summary
Designing indoor virtual spaces can be tiring because current tools don’t remember what users like from earlier sessions. The authors created SPHERE, a virtual reality tool that learns and remembers spatial preferences using natural user interactions like speech and hand movements. It uses smart models to keep designs stable and improves over time by learning from corrections users make. This approach helps users create personalized and consistent virtual room layouts with less effort and fewer mistakes.
What this means in practice
- •For virtual reality content creators: Create personalized indoor virtual scenes more efficiently by having the system remember and adapt to user spatial preferences across sessions.
- •For game designers: Use adaptive layout generation tools to reduce manual corrections when designing indoor game environments, improving design iteration speed.
Authors
Hyeonmin Lee, Zheng Wei, Kyungmin Kwon, Jumin Seo, Jiwon Park, Hayoung Oh
Abstract
While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making immersive authoring a repetitive and physically fatiguing process. We present SPHERE, an adaptive VR generation framework that transforms isolated synthesis into continuous human-AI co-creation. SPHERE extracts persistent spatial preferences from natural multimodal interactions (speech and controller edits). To ensure geometric resilience against spatial distortions, it abstracts these raw edits into hierarchical constraints modeling both local functional and global topological contexts. Furthermore, a human-in-the-loop reinforcement learning mechanism dynamically updates retrieval policies based on the user's final edited scenes. A mixed-design user study ($N=42$) and an offline ablation demonstrate that SPHERE significantly reduces corrective edits and physical demand, preventing bias toward shallow object-level traits to yield geometrically resilient, profile-aligned layouts. Ultimately, SPHERE demonstrates how capturing demonstrated spatial logic enables controlled spatial adaptation, establishing a reliable, governed human-AI collaboration framework for immersive authoring. Project page and source code will be available at: https://github.com/hyeonmin11/SPHERE