3D Indoor Scene Synthesis on Study Room (Generalization Split)
16.6Object Realism (OBR)LayoutGPT
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| LayoutGPTMethod Category=LLM-based few-shot learners2026.02 | 16.6 | 52.1 | 8.5 | 7.2 | 8.3 | 8 | |
| I-DesignMethod Category=LLM with post-processing2026.02 | 16.3 | 4.5 | 8.2 | 6.9 | 8.9 | 8 | |
| HolodeckMethod Category=LLM with post-processing2026.02 | 13.7 | 5.1 | 6.7 | 8.4 | 8.9 | 8 | |
| LayoutVLMMethod Category=LLM with post-processing2026.02 | 12.3 | 36.6 | 6.9 | 7.6 | 8.6 | 7.7 | |
| SceneReVisPolicy=Fine-tuned Qwen2.5-VL-7B, Reward Model=Qwen3-VL-235B, Algorithm=GRPO2026.02 | 0.5 | 2.1 | 8.2 | 8.3 | 8.9 | 8.5 |