Research map / 3D vision / 3D generation
Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation
Jialu Huang, Yingxuan You, Fei Wang, Zheng Dang
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 |
|---|---|---|---|
| add gradient-based refinement after evolutionary search in GPFS (ablation) | GPFS · Ablation subset | CF / PSA: CF 13.3 -> 100.0, PSA 0.0 -> 86.7 | Improved |
| add evolutionary global exploration before gradient descent in GPFS (ablation) | GPFS · Ablation subset | CF / PSA: CF 73.3 -> 100.0, PSA 61.3 -> 86.7 | Improved |
| add completeness verification in GSV (ablation) | GSV · Ablation subset | PSA: 74.0 -> 86.7 | Improved |
| add feasibility verification in GSV (ablation) | GSV · Ablation subset | CF / PSA: CF 93.3 -> 100.0, PSA 82.7 -> 86.7 | Improved |
| add semantic consistency verification in GSV (ablation) | GSV · Ablation subset | PSA: 85.3 -> 86.7 | Improved |
| replace GPT-4o with GPT-4.1 as VLM backbone | Ours · LayoutVLM benchmark avg | PSA: 78.5 -> 83.5 | Improved |
| graph verification plus hybrid search versus LayoutVLM | Ours vs LayoutVLM · LayoutVLM benchmark avg | PSA: 58.8 -> 83.5 | Improved |
| our method versus Holodeck on out-of-bound rate and navigability/accessibility | Ours vs Holodeck · SceneEval-100 | OOB / ACC / NAV: OOB 1.12 vs 2.09 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Holodeck — Holodeck: Language Guided Generation of 3D Embodied AI Environments (CVPR 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.92)
- Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model (AAAI 2025 · similarity 0.91)
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.91)
- Global-Local Tree Search in VLMs for 3D Indoor Scene Generation (CVPR 2025 · similarity 0.91)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · similarity 0.90)
- LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models (CVPR 2025 · similarity 0.90)
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.
