mlsanityData to 7 Oct 2026

Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation

arXiv 2104.13316 ↗First posted 27 Apr 2021cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Volumetric design is the first and critical step for professional building design, where architects not only depict the rough 3D geometry of the building but also specify the programs to form a 2D layout on each floor. Though 2D layout generation for a single story has been widely studied, there is no developed method for multi-story buildings. This paper focuses on volumetric design generation conditioned on an input program graph. Instead of outputting dense 3D voxels, we propose a new 3D representation named voxel graph that is both compact and expressive for building geometries. Our generator is a cross-modal graph neural network that uses a pointer mechanism to connect the input program graph and the output voxel graph, and the whole pipeline is trained using the adversarial framework. The generated designs are evaluated qualitatively by a user study and quantitatively using three metrics: quality, diversity, and connectivity accuracy. We show that our model generates realistic 3D volumetric designs and outperforms previous methods and baselines.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 27 Apr 2021.

Builds on

23 of 41 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2017Improved Training of Wasserstein GANscited by 2,223
  4. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 2015Pointer Networkscited by 882
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  8. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  9. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  10. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  11. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  12. 2017Submanifold Sparse Convolutional Networkscited by 223
11 more
  1. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  2. 2020House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generationcited by 86
  3. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  4. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56
  5. 2020Generative Layout Modeling using Constraint Graphscited by 46
  6. 2019Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstructioncited by 25
  7. 2020General 3D Room Layout from a Single View by Render-and-Comparecited by 21
  8. 2020LayoutGMN: Neural Graph Matching for Structural Layout Similaritycited by 19
  9. 2019Thinking Outside the Box: Generation of Unconstrained 3D Room Layoutscited by 10
  10. 2020Learning to simulate and design for structural engineeringcited by 9
  11. 2020End-to-end Generative Floor-plan and Layout with Attributes and Relation Graphcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 8; 2025: 3; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusioncited by 24
  2. 20253D Scene Generation: A Surveycited by 24
  3. 2023GlobalMapper: Arbitrary-Shaped Urban Layout Generationcited by 15
  4. 2024COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generationcited by 10
  5. 2024DreamView: Injecting View-specific Text Guidance into Text-to-3D Generationcited by 9
  6. 2024Leveraging Generative AI for Urban Digital Twins: A Scoping Review on the Autonomous Generation of Urban Data, Scenarios, Designs, and 3D City Models for Smart City Advancementcited by 7
  7. 2024Constrained Layout Generation with Factor Graphscited by 6
  8. 2022Vitruvio: 3D Building Meshes via Single Perspective Sketchescited by 5
  9. 2024Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generationcited by 5
  10. 2023AutoEncoding Tree for City Generation and Applicationscited by 3
  11. 2025Computer-Aided Layout Generation for Building Design: A Reviewcited by 3
  12. 2026Deep Sketch-Based 3D Modeling: A Surveycited by 3
8 more
  1. 2023Automating Computational Design with Generative AIcited by 2
  2. 2023Representation Learning for Sequential Volumetric Design Taskscited by 2
  3. 2024RoBus: A Multimodal Dataset for Controllable Road Networks and Building Layouts Generationcited by 2
  4. 2026ShellMaker: Language-Guided Exterior Completion under Structural Constraintscited by 2
  5. 2023Integrating Symbolic Reasoning into Neural Generative Models for Design Generationcited by 1
  6. 2024CGGM: A conditional graph generation model with adaptive sparsity for node anomaly detection in IoT networkscited by 0
  7. 2024ArchComplete: Autoregressive 3D Architectural Design Generation with Hierarchical Diffusion-Based Upsamplingcited by 0
  8. 2025ArchShapeNet:An Interpretable 3D-CNN Framework for Evaluating Architectural Shapescited by 0