Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Xianhui Meng, Zirui Song, Yuchen Zhang, Li Zhang, Yongxuan Lv, Xiuying Chen, Kun Wang, Yan Luo, Kai Chen, Hangjun Ye, Long Chen, Jun Liu, Xiaoshuai Hao
• Venue: arXiv: cs.AI
• Published: 2026-07-02
• Collected: 2026-07-03
• URL: http://arxiv.org/abs/2607.02407v1
• PDF: https://arxiv.org/pdf/2607.02407v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers propose a new framework, SPG-Layout, to generate physically plausible indoor scenes in complex non-Manhattan environments. The framework uses statistical priors of object distributions and a hierarchical layout strategy to optimize semantic realism and physical plausibility. Experiments show that SPG-Layout outperforms existing methods across both Manhattan and non-Manhattan environments.

What the Document Says

• The research proposes SPG-Layout, a text-driven framework for generating indoor scenes in complex non-Manhattan environments.
• SPG-Layout uses statistical priors of object distributions to guide training for better environmental understanding and fidelity.
• A hierarchical layout strategy is adopted that prioritizes large objects placement to minimize layout violations.
• The aim is to achieve a balance between semantic realism and physical plausibility.
• A new benchmark with 500 diverse non-Manhattan environments was constructed for evaluation.
• Extensive experiments show SPG-Layout outperforms existing methods in both Manhattan and non-Manhattan environments.

Key Concepts Mentioned

• SPG-Layout
• 3D indoor synthesis
• non-Manhattan environments
• statistical priors
• hierarchical layout strategy
• semantic realism
• physical plausibility

Claims Made by the Document

• Existing methods fail to capture plausible object layout patterns in non-Manhattan settings.
• SPG-Layout addresses this challenge by proposing a novel text-driven framework.

Evidence Used

• The text mentions that existing methods struggle with non-orthogonal spatial relationships leading to high geometric violations and low physical fidelity.
• The text states SPG-Layout achieves a balanced optimization of semantic realism and physical plausibility.
• The text mentions extensive experiments showing SPG-Layout outperforms existing methods.

Methods / Approach

• Use of statistical priors of object distributions
• Hierarchical layout strategy

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The proposed method might not address all potential limitations in the field, as it's based on the current understanding and capabilities of Large Language Models.

Open Questions

• What specific methods are used for the hierarchical layout strategy?
• What metrics were used to evaluate performance?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The text implies that existing methods struggle with non-orthogonal spatial relationships but does not specify which exact methods it refers to.
• The text mentions extensive experiments but does not detail the specific metrics used for evaluation.

Raw Abstract / Excerpt

Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible object layout patterns in non-Manhattan settings, primarily because they struggle to model non-orthogonal spatial relationships, leading to high geometric violations and low physical fidelity. To address this challenge, we propose SPG-Layout, a novel text-driven framework designed to generate physically plausible indoor scenes within complex non-Manhattan environments. Specifically, we first utilize statistical priors of object distributions to guide the training process, enhancing environmental understanding and fidelity. Furthermore, mirroring human design workflows, we adopt a hierarchical layout strategy that prioritizes the placement of large objects, thereby substantially minimizing layout violations. By synergizing these components, SPG-Layout achieves a balanced optimization of semantic realism and physical plausibility. To evaluate performance in these complex settings, we constructed a new benchmark comprising 500 diverse non-Manhattan environments. Extensive experiments demonstrate that SPG-Layout consistently and significantly outperforms existing methods across both Manhattan and non-Manhattan environments. The code will be publicly released.