Research map / 3D vision / 3D generation
M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation
Yiheng Zhang, Zhuojiang Cai, Mingdao Wang, Meitong Guo, Tianxiao Li, Li Lin, Yuwang Wang
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 |
|---|---|---|---|
| train diffusion layout model on M3DLayout instead of DiffuScene training data | DIFF-M3DLayout · Matterport reference | FID: 98.03 -> 87.89 | Improved |
| train diffusion layout model on M3DLayout | DIFF-M3DLayout · Inf3DLayout reference | FID: 102.12 -> 70.85 | Improved |
| train diffusion layout model on M3DLayout | DIFF-M3DLayout · 3D-FRONT reference | FID: 29.47 -> 57.64 | Hurt |
| use autoregressive generation on M3DLayout | AR-M3DLayout · Inf3DLayout reference | FID: 102.12 -> 57.90 | Improved |
| use autoregressive generation on M3DLayout | AR-M3DLayout · 3D-FRONT reference | FID: 29.47 -> 87.98 | Hurt |
| train on M3DLayout (richer small-object data) | AR-M3DLayout · Text-to-layout | CLIP-Score: 0.1982 -> 0.2026 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DiffuScene — DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis (CVPR 2024) · better on 5 of 7 shared results
- InstructScene — InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024) · better on 7 of 7 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 0.93)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (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)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.91)
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 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.
