Metraipolis › archive › dc_89710b6687de

SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL — arXiv:2610.02023

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02023
License (as archived)
CC0-1.0
Archived
2026-10-06T12:06:47.107Z
SHA-256 of the archived text
be7898fb19d1a5fe55c3bd709a900720e93b6ee33e9b6368fee01aa390615cbc
Stable URL of this page
https://metraipolis.com/documento/dc_89710b6687de

How to cite

SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL — arXiv:2610.02023 — arXiv (en), https://arxiv.org/abs/2610.02023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89710b6687de (Metraipolis archive dc_89710b6687de, sha256 be7898fb19d1a5fe55c3bd709a900720e93b6ee33e9b6368fee01aa390615cbc)
BibTeX
@misc{dc89710b6687de,
  title = {SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL — arXiv:2610.02023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89710b6687de; sha256 be7898fb19d1a5fe55c3bd709a900720e93b6ee33e9b6368fee01aa390615cbc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.02023 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T10:21:27.992Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).