Unified Vector Floorplan Generation via Markup Representation

• URL: http://arxiv.org/abs/2604.04859v1
• Date: Mon, 06 Apr 2026 17:04:30 GMT
• Title: Unified Vector Floorplan Generation via Markup Representation
• Abstract summary: We introduce Floorplan Markup Language (FML), a representation that encodes floorplan information within a single structured grammar.<n>We develop a transformer-based generative model, FMLM, capable of producing high-fidelity and functional floorplans under diverse conditions.
• Score: 36.228613615394856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic residential floorplan generation has long been a central challenge bridging architecture and computer graphics, aiming to make spatial design more efficient and accessible. While early methods based on constraint satisfaction or combinatorial optimization ensure feasibility, they lack diversity and flexibility. Recent generative models achieve promising results but struggle to generalize across heterogeneous conditional tasks, such as generation from site boundaries, room adjacency graphs, or partial layouts, due to their suboptimal representations. To address this gap, we introduce Floorplan Markup Language (FML), a general representation that encodes floorplan information within a single structured grammar, which casts the entire floorplan generation problem into a next token prediction task. Leveraging FML, we develop a transformer-based generative model, FMLM, capable of producing high-fidelity and functional floorplans under diverse conditions. Comprehensive experiments on the RPLAN dataset demonstrate that FMLM, despite being a single model, surpasses the previous task-specific state-of-the-art methods.

Related papers

• HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation [0.8699280339422538]
  We propose a novel approach to generation of floor plans based on learning hypergraph representations with a large language model (LLM)<n>We show that the proposed methodology offers a high degree of editability, making it well suited to design-oriented supported by LLMs.
  arXiv  Detail & Related papers  (2026-05-18T15:00:29Z)
• TodoEvolve: Learning to Architect Agent Planning Systems [68.48983335970901]
  TodoEvolve is a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning.<n>PlanFactory provides a common interface for heterogeneous planning patterns.<n>TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.
  arXiv  Detail & Related papers  (2026-02-08T06:37:01Z)
• TLC-Plan: A Two-Level Codebook Based Network for End-to-End Vector Floorplan Generation [19.063941053235567]
  We propose TLC-Plan, a hierarchical generative model that directly synthesizes vectors from spatial input boundaries.<n>TLC-Plan employs a two-level VQ-VAE to encode global layouts as semantically labeled room bounding boxes.<n>Experiments show state-of-the-art performance on RPLAN dataset and leading results on LI dataset.
  arXiv  Detail & Related papers  (2026-02-06T15:36:50Z)
• FloorplanVLM: A Vision-Language Model for Floorplan Vectorization [15.691267151619442]
  We present FloorplanVLM, a unified framework that reformulates vectorization as an image-conditioned sequence modeling task.<n>This 'pixels-to-sequence' paradigm enables the precise and holistic constraint satisfaction of complex grounding, such as walls and curved arcs.
  arXiv  Detail & Related papers  (2026-02-06T08:57:52Z)
• OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models [57.94189874119267]
  Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems.<n>Current graph learning-based design methodologies often adhere to a "one-for-one" paradigm.<n>We propose OFA-TAD, a one-for-all framework that generates adaptive collaboration graphs for any task described in natural language.
  arXiv  Detail & Related papers  (2026-01-19T12:23:44Z)
• FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction [25.35768485637194]
  Existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a single pass.<n>We propose a novel 'next room prediction' paradigm tailored to architectural floor plan modeling.<n> FPDS demonstrates competitive performance in comparison to diffusion models and Tell2Design in the text-to-floorplan task.
  arXiv  Detail & Related papers  (2025-06-12T04:33:27Z)
• HouseTune: Two-Stage Floorplan Generation with LLM Assistance [10.558141230827847]
  This paper proposes a two-stage text-to-floorplan framework that combines the reasoning capability of Large Language Models with the generative power of diffusion models.<n> Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, which validates its effectiveness in practical home design applications.
  arXiv  Detail & Related papers  (2024-11-19T06:57:45Z)
• PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM [58.67882997399021]
  Our research introduces a unified framework for automated graphic layout generation.<n>Our data-driven method employs structured text (JSON format) and visual instruction tuning to generate layouts.<n>We develop an automated text-to-poster system that generates editable posters based on users' design intentions.
  arXiv  Detail & Related papers  (2024-06-05T03:05:52Z)
• Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty [56.30846158280031]
  Task planning for embodied AI has been one of the most challenging problems. We propose a task-agnostic method named 'planning as in-painting' The proposed framework achieves promising performances in various embodied AI tasks.
  arXiv  Detail & Related papers  (2023-12-02T10:07:17Z)
• Compositional Foundation Models for Hierarchical Planning [52.18904315515153]
  We propose a foundation model which leverages expert foundation model trained on language, vision and action data individually together to solve long-horizon tasks. We use a large language model to construct symbolic plans that are grounded in the environment through a large video diffusion model. Generated video plans are then grounded to visual-motor control, through an inverse dynamics model that infers actions from generated videos.
  arXiv  Detail & Related papers  (2023-09-15T17:44:05Z)
• Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning [36.300564378022315]
  We present a learning-enabled Task and Motion Planning (TAMP) algorithm for solving mobile manipulation problems in environments with many articulated and movable obstacles. The core of our algorithm is PIGINet, a novel Transformer-based learning method that takes in a task plan, the goal, and the initial state, and predicts the probability of finding motion trajectories associated with the task plan.
  arXiv  Detail & Related papers  (2022-11-03T04:12:04Z)
• Differentiable Spatial Planning using Transformers [87.90709874369192]
  We propose Spatial Planning Transformers (SPT), which given an obstacle map learns to generate actions by planning over long-range spatial dependencies. In the setting where the ground truth map is not known to the agent, we leverage pre-trained SPTs in an end-to-end framework. SPTs outperform prior state-of-the-art differentiable planners across all the setups for both manipulation and navigation tasks.
  arXiv  Detail & Related papers  (2021-12-02T06:48:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.