Research map / Image generation / Autoregressive and latent generation
Unified Vector Floorplan Generation via Markup Representation
Kaede Shiohara, Toshihiko Yamasaki
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 room permutation augmentation (ablation) | FMLM · boundary+graph | FID: 24.36 -> 14.17 | Improved |
| add room permutation augmentation (ablation) | FMLM · boundary+graph | GED: 2.35 -> 1.24 | Improved |
| index rooms in descending instead of ascending order (ablation) | FMLM · number-conditional | FID: 94.57 -> 25.50 | Improved |
| add constrained decoding (ablation) | FMLM · unconditional | validity | Improved |
| FMLM vs Graph2Plan on boundary | FMLM · RPLAN boundary | FID: 34.20 -> 6.51 | Improved |
| FMLM vs GSDiff on boundary | FMLM · RPLAN boundary | FID: 11.26 -> 4.61 | Improved |
| FMLM vs GSDiff unconditional | FMLM · RPLAN unconditional | FID: 15.02 -> 7.22 | Improved |
| FMLM vs HouseDiffusion on graph (all) | FMLM · RPLAN graph | GED: 1.55 -> 1.21 | Improved |
| FMLM vs HouseDiffusion on graph with 8 rooms | FMLM · RPLAN graph (8 rooms) | GED: 1.87 -> 1.96 | Hurt |
| FMLM vs Graph2Plan on boundary+graph | FMLM · RPLAN boundary+graph | FID: 22.87 -> 14.17 | 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.
- HouseDiffusion — HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising (CVPR 2023) · better on 2 of 3 shared results
- HouseGAN++ — House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation (ECCV 2020) · better on 2 of 2 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
- HouseTune: Two-Stage Floorplan Generation with LLM Assistance (AAAI 2026 · similarity 0.91)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.90)
- MaskPLAN: Masked Generative Layout Planning from Partial Input (CVPR 2024 · similarity 0.87)
- Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans (CVPR 2026 · similarity 0.87)
- Constrained Layout Generation with Factor Graphs (CVPR 2024 · similarity 0.86)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · similarity 0.85)
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.
