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

arXiv: https://arxiv.org/abs/2602.07100 · HTML: https://mlsanity.com/paper/2602.07100/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 51 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation](https://mlsanity.com/paper/2402.14744/) (2024)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation](https://mlsanity.com/paper/2003.06988/) (2020)
- [I-Design: Personalized LLM Interior Designer](https://mlsanity.com/paper/2404.02838/) (2024)
- [Hierarchical Neural Coding for Controllable CAD Model Generation](https://mlsanity.com/paper/2307.00149/) (2023)
- [HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising](https://mlsanity.com/paper/2211.13287/) (2022)
- [CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs](https://mlsanity.com/paper/2412.19663/) (2024)
- [Generative Layout Modeling using Constraint Graphs](https://mlsanity.com/paper/2011.13417/) (2020)
- [Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks](https://mlsanity.com/paper/1611.05916/) (2016)
- [Graph2Plan: Learning Floorplan Generation from Layout Graphs](https://mlsanity.com/paper/2004.13204/) (2020)
- [From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach](https://mlsanity.com/paper/2412.11892/) (2024)
- [ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Design](https://mlsanity.com/paper/2111.03545/) (2021)
- [Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework](https://mlsanity.com/paper/2408.08054/) (2024)
- [iPLAN: Interactive and Procedural Layout Planning](https://mlsanity.com/paper/2203.14412/) (2022)
- [GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation](https://mlsanity.com/paper/2408.16258/) (2024)
- [Revisiting CAD Model Generation by Learning Raster Sketch](https://mlsanity.com/paper/2503.00928/) (2025)
- [Eliminating Rasterization: Direct Vector Floor Plan Generation with DiffPlanner](https://mlsanity.com/paper/2508.13738/) (2025)
- [Computer-Aided Layout Generation for Building Design: A Review](https://mlsanity.com/paper/2504.09694/) (2025)
- [CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction](https://mlsanity.com/paper/2509.15459/) (2025)

## Abstract (arXiv)

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.