Raster-to-Graph: Floorplan Recognition via Autoregressive Graph Prediction with an Attention Transformer

Abstract

Recognizing the detailed information embedded in rasterized floorplans is at the research forefront in the community of computer graphics and vision. With the advent of deep neural networks, automatic floorplan recognition has made tremendous breakthroughs. However, co-recognizing both the structures and semantics of floorplans through one neural network remains a significant challenge. In this paper, we introduce a novel framework Raster-to-Graph, which automatically achieves structural and semantic recognition of floorplans.We represent vectorized floorplans as structural graphs embedded with floorplan semantics, thus transforming the floorplan recognition task into a structural graph prediction problem. We design an autoregressive prediction framework using the neural network architecture of the visual attention Transformer, iteratively predicting the wall junctions and wall segments of floorplans in the order of graph traversal. Additionally, we propose a large-scale floorplan dataset containing over 10,000 real-world residential floorplans. Our autoregressive framework can automatically recognize the structures and semantics of floorplans. Extensive experiments demonstrate the effectiveness of our framework, showing significant improvements on all metrics. Qualitative and quantitative evaluations indicate that our framework outperforms existing state-of-the-art methods. Code and dataset for this paper are available at: https://github.com/HSZVIS/Raster-to-Graph.