Research map / 3D vision / 3D generation
Repurposing 3D Generative Model for Autoregressive Layout Generation
Haoran Feng, Yifan Niu, Zehuan Huang, Yang-Tian Sun, Chunchao Guo, Yuxin Peng, Lu Sheng
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 identity-aware embedding (ablation) | base 3D generative model · LayoutVLM layout benchmark | PSA: 16.7 -> 71.4 | Improved |
| add identity-aware embedding (ablation) | base 3D generative model · LayoutVLM layout benchmark | collision-free (CF): 75.6 -> 89.1 | Improved |
| add holistic-guidance distillation (ablation) | base + id-aware embedding · LayoutVLM layout benchmark | generation time (s): 144.1 -> 24.5 | Improved |
| add holistic-guidance distillation (ablation) | base + id-aware embedding · LayoutVLM layout benchmark | PSA: 71.4 -> 59.7 | Hurt |
| add step-wise guidance (ablation) | base + id-aware + holistic guidance · LayoutVLM layout benchmark | PSA: 59.7 -> 78.8 | Improved |
| add step-wise guidance (ablation) | base + id-aware + holistic guidance · LayoutVLM layout benchmark | collision-free (CF): 79.5 -> 97.3 | Improved |
| add step-wise guidance (ablation) | base + id-aware + holistic guidance · LayoutVLM layout benchmark | rotation coherency: 58.7 -> 77.1 | Improved |
| use LaviGen instead of LayoutVLM | LayoutVLM · LayoutVLM layout benchmark | PSA: 58.8 -> 78.8 | Improved |
| use LaviGen instead of LayoutVLM | LayoutVLM · LayoutVLM layout benchmark | generation time (s): 75.5 -> 24.3 | Improved |
| use LaviGen instead of LayoutGPT | LayoutGPT · LayoutVLM layout benchmark | positional coherency: 80.8 -> 76.9 | Hurt |
| use LaviGen instead of LayoutVLM | LayoutVLM · User study | overall quality preference: 36.5 -> 55.6 | 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 4 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
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.90)
- Disentangled 3D Scene Generation with Layout Learning (ICML 2024 · similarity 0.89)
- Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint (ICLR 2025 · similarity 0.88)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.88)
- DeBaRA: Denoising-Based 3D Room Arrangement Generation (NeurIPS 2024 · similarity 0.87)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image 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.
