Research map / 3D vision / 3D generation
Human-Centric Indoor Scene Synthesis Using Stochastic Grammar
Siyuan Qi, Yixin Zhu, Siyuan Huang, Chenfanfu Jiang, Song-Chun Zhu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use human-centric S-AOG scene synthesis instead of Yu et al.'s arrangement method | indoor scene synthesis · SUNCG segmentation maps | classifier accuracy (%): 87.49 -> 76.18 | Improved |
| add human constraints and contextual relations to scene generation (ablation) | indoor scene synthesis · Bedroom layouts | functionality rating: 1.25 ± 0.43 -> 4.67 ± 0.90 | Improved |
| add human constraints and contextual relations to scene generation (ablation) | indoor scene synthesis · Bedroom layouts | naturalness rating: 1.00 ± 0.00 -> 4.25 ± 0.66 | Improved |
| add human constraints to object-wise relation modeling (ablation) | indoor scene synthesis · Bedroom layouts | functionality rating: 3.62 ± 1.22 -> 4.67 ± 0.90 | Improved |
| add human constraints to object-wise relation modeling (ablation) | indoor scene synthesis · Bedroom layouts | naturalness rating: 3.12 ± 1.17 -> 4.25 ± 0.66 | Improved |
| pre-train on synthesized data before NYUv2 fine-tuning | depth estimation model · NYU-Depth V2 | Abs Rel: 0.233 -> 0.226 | Improved |
| pre-train on synthesized data before NYUv2 fine-tuning | surface normal estimation model · NYU-Depth V2 | mean angular error: 21.74 -> 21.47 | Improved |
Closest papers by meaning
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.89)
- Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model (AAAI 2025 · similarity 0.88)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · similarity 0.88)
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.88)
- S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field (AAAI 2025 · similarity 0.87)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
