# FloorplanVLM: A Vision-Language Model for Floorplan Vectorization

arXiv: https://arxiv.org/abs/2602.06507 · HTML: https://mlsanity.com/paper/2602.06507/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [ChartLlama: A Multimodal LLM for Chart Understanding and Generation](https://mlsanity.com/paper/2311.16483/) (2023)
- [SpaceR: Reinforcing MLLMs in Video Spatial Reasoning](https://mlsanity.com/paper/2504.01805/) (2025)
- [End-to-End Wireframe Parsing](https://mlsanity.com/paper/1905.03246/) (2019)
- [CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis](https://mlsanity.com/paper/1904.01920/) (2019)
- [Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries](https://mlsanity.com/paper/2211.15658/) (2022)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models](https://mlsanity.com/paper/2512.06328/) (2025)
- [PolyRoom: Room-aware Transformer for Floorplan Reconstruction](https://mlsanity.com/paper/2407.10439/) (2024)

## Built on by (most cited first, 5 of 5)

- [Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans](https://mlsanity.com/paper/2606.10953/) (2026)
- [Towards an automated AI-based framework for floor plan compliance checks for residential buildings](https://mlsanity.com/paper/2607.00015/) (2026)
- [When Should a Network Emit Geometry, and When Should It Detect It? Readout, Reconciliation, and Representation in Floorplan Vectorization](https://mlsanity.com/paper/2608.25608/) (2026)
- [Evidence-gated multimodal parsing and vectorization of architectural floor plans](https://mlsanity.com/paper/2609.25615/) (2026)
- [K-OPSD: Verifiable On-Policy Self-Distillation for Post-Training Vision-Language Models on AEC Drawings](https://mlsanity.com/paper/2609.34082/) (2026)

## Abstract (arXiv)

Converting raster floorplans into engineering-grade vector graphics is challenging due to complex topology and strict geometric constraints. To address this, we present FloorplanVLM, a unified framework that reformulates floorplan vectorization as an image-conditioned sequence modeling task. Unlike pixel-based methods that rely on fragile heuristics or query-based transformers that generate fragmented rooms, our model directly outputs structured JSON sequences representing the global topology. This 'pixels-to-sequence' paradigm enables the precise and holistic constraint satisfaction of complex geometries, such as slanted walls and curved arcs. To support this data-hungry approach, we introduce a scalable data engine: we construct a large-scale dataset (Floorplan-2M) and a high-fidelity subset (Floorplan-HQ-300K) to balance geometric diversity and pixel-level precision. We then employ a progressive training strategy, using Supervised Fine-Tuning (SFT) for structural grounding and quality annealing, followed by Group Relative Policy Optimization (GRPO) for strict geometric alignment. To standardize evaluation on complex layouts, we establish and open-source FPBench-2K. Evaluated on this rigorous benchmark, FloorplanVLM demonstrates exceptional structural validity, achieving 92.52% external-wall IoU and robust generalization across non-Manhattan architectures.