Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
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 prior
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorXianhui Meng →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorZirui Song →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorYuchen Zhang →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorLi Zhang →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorYongxuan Lv →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorXiuying Chen →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorKun Wang →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorYan Luo →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorKai Chen →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorHangjun Ye →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorTianlong Chen →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorJun Liu →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
- Linked via arxiv authorXiaoshuai Hao →
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments