ResPlan: A Large-Scale Vector-Graph Dataset of 17,000 Residential Floor Plans

2025-08-19

AI Summary

Existing residential floor plan datasets (e.g., RPLAN, MSD) suffer from low visual fidelity, limited structural diversity, and excessive idealization, hindering spatial intelligence research in realistic settings. To address these limitations, we introduce a large-scale vectorized floor plan dataset comprising 17,000 high-fidelity, non-idealized residential plans. Our method pioneers room connectivity graph representation and open-sources geometric cleaning and fine-grained annotation pipelines. The dataset adopts a dual-modality geometric + graph-structured representation, with precise semantic annotations for architectural elements and functional spaces, enabling seamless integration with simulation engines and efficient 3D reconstruction. Quantitative and qualitative evaluations demonstrate substantial improvements over prior benchmarks in structural richness, realism, and cross-task generalizability—particularly for spatial understanding and generative tasks. The dataset is publicly released to foster open research in embodied AI and digital twin applications.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Web data integration and cleaning

Abstract

We introduce ResPlan, a large-scale dataset of 17,000 detailed, structurally rich, and realistic residential floor plans, created to advance spatial AI research. Each plan includes precise annotations of architectural elements (walls, doors, windows, balconies) and functional spaces (such as kitchens, bedrooms, and bathrooms). ResPlan addresses key limitations of existing datasets such as RPLAN (Wu et al., 2019) and MSD (van Engelenburg et al., 2024) by offering enhanced visual fidelity and greater structural diversity, reflecting realistic and non-idealized residential layouts. Designed as a versatile, general-purpose resource, ResPlan supports a wide range of applications including robotics, reinforcement learning, generative AI, virtual and augmented reality, simulations, and game development. Plans are provided in both geometric and graph-based formats, enabling direct integration into simulation engines and fast 3D conversion. A key contribution is an open-source pipeline for geometry cleaning, alignment, and annotation refinement. Additionally, ResPlan includes structured representations of room connectivity, supporting graph-based spatial reasoning tasks. Finally, we present comparative analyses with existing benchmarks and outline several open benchmark tasks enabled by ResPlan. Ultimately, ResPlan offers a significant advance in scale, realism, and usability, providing a robust foundation for developing and benchmarking next-generation spatial intelligence systems.

Problem

• Addresses limitations of existing residential floor plan datasets
• Provides enhanced visual fidelity and structural diversity
• Supports spatial AI research with versatile geometric and graph formats

Innovation

• Large-scale vector-graph dataset creation
• Open-source geometry cleaning pipeline
• Structured room connectivity representations