FloorGenT: Generative Vector Graphic Model of Floor Plans for Robotics
Not on the map. Why?
Abstract (arXiv)
Floor plans are the basis of reasoning in and communicating about indoor environments. In this paper, we show that by modelling floor plans as sequences of line segments seen from a particular point of view, recent advances in autoregressive sequence modelling can be leveraged to model and predict floor plans. The line segments are canonicalized and translated to sequence of tokens and an attention-based neural network is used to fit a one-step distribution over next tokens. We fit the network to sequences derived from a set of large-scale floor plans, and demonstrate the capabilities of the model in four scenarios: novel floor plan generation, completion of partially observed floor plans, generation of floor plans from simulated sensor data, and finally, the applicability of a floor plan model in predicting the shortest distance with partial knowledge of the environment.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 7 Mar 2022.
Builds on
17 of 27 references.
References · 17
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Layer Normalizationcited by 5,579
- 2019The Curious Case of Neural Text Degenerationcited by 2,881
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
- 2016Conditional Image Generation with PixelCNN Decoderscited by 859
- 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
- 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 260
- 2021Thinking Like Transformerscited by 182
- 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
5 more
- 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 129
- 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
- 2019Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Pathcited by 35
- 2019Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attentioncited by 27
- 2020Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environmentscited by 20
Built on by
Citing papers per year: 2024: 1.
1 paper.