TLC-Plan: A Two-Level Codebook Based Network for End-to-End Vector Floorplan Generation

TL;DR

TLC-Plan introduces a hierarchical, vector-based generative model for floorplan creation that directly produces topologically valid designs, improving over raster-based methods and enabling end-to-end architectural modeling.

Contribution

It proposes a novel two-level VQ-VAE and CodeTree hierarchy for direct vector floorplan synthesis, advancing the state-of-the-art in end-to-end architectural design generation.

Findings

Achieves state-of-the-art FID score of 1.84 on RPLAN dataset.

Generates diverse, topologically valid floorplans without explicit priors.

Outperforms existing methods on multiple datasets.

Abstract

Automated floorplan generation aims to improve design quality, architectural efficiency, and sustainability by jointly modeling global spatial organization and precise geometric detail. However, existing approaches operate in raster space and rely on post hoc vectorization, which introduces structural inconsistencies and hinders end-to-end learning. Motivated by compositional spatial reasoning, we propose TLC-Plan, a hierarchical generative model that directly synthesizes vector floorplans from input boundaries, aligning with human architectural workflows based on modular and reusable patterns. TLC-Plan employs a two-level VQ-VAE to encode global layouts as semantically labeled room bounding boxes and to refine local geometries using polygon-level codes. This hierarchy is unified in a CodeTree representation, while an autoregressive transformer samples codes conditioned on the boundary to generate diverse and topologically valid designs, without requiring explicit room topology or dimensional priors. Extensive experiments show state-of-the-art performance on RPLAN dataset (FID = 1.84, MSE = 2.06) and leading results on LIFULL dataset. The proposed framework advances constraint-aware and scalable vector floorplan generation for real-world architectural applications. Source code and trained models are released at https://github.com/rosolose/TLC-PLAN.