GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework

TL;DR

<3-5 sentence high-level summary> GreenPlanner tackles the challenge of generating floorplans that are both spatially feasible and energy-efficient by intertwining rapid feasibility evaluation with controllable generation. It introduces DesignFD to encode constraint priors, PDE to predict energy and feasibility, GreenPD to provide a fully compliant dataset, and GreenFlow to generate layouts conditioned on regulatory requirements. The framework substantially accelerates evaluation, eliminates infeasible samples, and improves design efficiency compared with professional architects, while delivering superior spatial realism and energy performance. This end-to-end, constraint-aware pipeline enables scalable, real-world floorplan design with potential for broad adoption in regulatory-compliant architectural workflows.

Abstract

Building design directly affects human well-being and carbon emissions, yet generating spatial-functional and energy-compliant floorplans remains manual, costly, and non-scalable. Existing methods produce visually plausible layouts but frequently violate key constraints, yielding invalid results due to the absence of automated evaluation. We present GreenPlanner, an energy- and functionality-aware generative framework that unifies design evaluation and generation. It consists of a labeled Design Feasibility Dataset for learning constraint priors; a fast Practical Design Evaluator (PDE) for predicting energy performance and spatial-functional validity; a Green Plan Dataset (GreenPD) derived from PDE-guided filtering to pair user requirements with regulation-compliant layouts; and a GreenFlow generator trained on GreenPD with PDE feedback for controllable, regulation-aware generation. Experiments show that GreenPlanner accelerates evaluation by over $10^{5}\times$ with $>$99% accuracy, eliminates invalid samples, and boosts design efficiency by 87% over professional architects.

Figures (6)

• Figure 1: Comparison of model performance in terms of reasonableness (higher is better), energy EUI (lower is better), and FID (bubble size, larger is better). Our method achieves higher spatial plausibility, significantly lower energy consumption, and better generation quality, surpassing existing approaches overall.
• Figure 2: Overview of our GreenPlanner, an energy- and functional-aware generative framework for residential layout design. It consists of four key components: (1) Design Feasibility Dataset (DesignFD), a dataset derived from RPLAN through quantitative energy and functional evaluations; (2) the Practical Design Evaluator (PDE), a convolutional network trained on DesignFD to predict design metrics rapidly; (3) Green Plan Dataset (GreenPD), a fully regulation-compliant demand–plan dataset refined via PDE-guided resampling; and (4) the GreenFlow generator, trained and fine-tuned under PDE feedback for controllable, regulation-aware floorplan generation. Together, these components form an end-to-end pipeline from data construction to constraint-driven generative design.
• Figure 3: Comparison between the original RPLAN dataset and our proposed GreenPD. While RPLAN contains numerous violations in energy, safety, and functional constraints, GreenPD achieves complete compliance with all physical design standards.
• Figure 4: Qualitative comparison of layout generation results. Baseline models (e.g., HouseDiffusion, HouseGAN++) often fail to produce necessary openings (doors and windows), resulting in functional incomplete layouts and unrealistic energy performance. For fair evaluation, a small number of openings were randomly inserted into their outputs to enable energy assessment. Our GreenFlow generates layouts with coherent spatial organization and complete openings.
• Figure 5: Energy controllability under different energy targets. Each model is evaluated at four target EUI levels (110, 120, 130, 140). Models trained on GreenPD (w/o RL and Full Model) are tested under both Graph and Edge inputs. Deviations at 110 EUI arise from functional constraints (e.g., kitchens).