End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement

TL;DR

This paper introduces a novel two-stage framework for generating vectorized floorplans from user inputs, utilizing graph convolutional and transformer networks, with a panoptic refinement step for improved design quality and connectivity.

Contribution

The paper presents a new end-to-end method for vectorized floorplan generation that incorporates a panoptic refinement network for enhanced accuracy and visual appeal.

Findings

Achieves state-of-the-art performance on real-world datasets.

Effectively maintains room connectivity with geometric loss.

Produces high-fidelity, editable vectorized floorplans.

Abstract

The automatic generation of floorplans given user inputs has great potential in architectural design and has recently been explored in the computer vision community. However, the majority of existing methods synthesize floorplans in the format of rasterized images, which are difficult to edit or customize. In this paper, we aim to synthesize floorplans as sequences of 1-D vectors, which eases user interaction and design customization. To generate high fidelity vectorized floorplans, we propose a novel two-stage framework, including a draft stage and a multi-round refining stage. In the first stage, we encode the room connectivity graph input by users with a graph convolutional network (GCN), then apply an autoregressive transformer network to generate an initial floorplan sequence. To polish the initial design and generate more visually appealing floorplans, we further propose a novel panoptic refinement network(PRN) composed of a GCN and a transformer network. The PRN takes the initial generated sequence as input and refines the floorplan design while encouraging the correct room connectivity with our proposed geometric loss. We have conducted extensive experiments on a real-world floorplan dataset, and the results show that our method achieves state-of-the-art performance under different settings and evaluation metrics.