Research map / 3D vision / 3D generation
HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models
Haiyan Jiang, Deyu Zhang, Dongdong Weng, Weitao Song, Henry Been-Lirn Duh
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 hierarchical optimization (ablation) | HOG-Layout · SceneEval-100 | COL_sc (%): 65.00 -> 16.00 | Improved |
| add hierarchical optimization (ablation) | HOG-Layout · SceneEval-100 | OAR (%): 62.55 -> 75.74 | Improved |
| add hierarchical optimization (ablation) | HOG-Layout · SceneEval-100 | NAV (%): 98.69 -> 97.15 | Hurt |
| use hierarchical force optimizer instead of gradient-based optimizer (ablation) | HOG-Layout · SceneEval-100 | Time (s): 147.93 -> 70.44 | Improved |
| use hierarchical force optimizer instead of gradient-based optimizer (ablation) | HOG-Layout · SceneEval-100 | COL_sc (%): 28.00 -> 16.00 | Improved |
| add RAG layout rule library to planning (ablation) | HOG-Layout · SceneEval-100 | OOR (%): 37.89 -> 43.09 | Improved |
| add RAG layout rule library to planning (ablation) | HOG-Layout · SceneEval-100 | OAR (%): 68.98 -> 75.74 | Improved |
| add object data to planning module (ablation) | HOG-Layout · SceneEval-100 | OAR (%): 65.07 -> 75.74 | Improved |
| add layout description to planning module (ablation) | HOG-Layout · SceneEval-100 | OAR (%): 67.14 -> 75.74 | Improved |
| add object data to planning module (ablation) | HOG-Layout · SceneEval-100 | SP: 65.61 -> 69.69 | Improved |
| use full planning module instead of room planning only (ablation) | HOG-Layout · SceneEval-100 | SP: 68.02 -> 69.69 | Improved |
| add grid lines to the VLM top-down image (ablation) | HOG-Layout · SceneEval-100 | OAR (%): 67.60 -> 75.74 | Improved |
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 3 of 4 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
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent (NeurIPS 2025 · similarity 0.90)
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.88)
- EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing (ICLR 2025 · similarity 0.88)
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.87)
- Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model (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.
