mlsanityData to 14 Oct 2026

Generating 3D House Wireframes with Semantics

arXiv 2407.12267 ↗First posted 17 Jul 2024cs.CV cs.GRcited by 8

Not on the map. Why?

Abstract (arXiv)

We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-based representation for improved coherence in learning 3D wireframe structures. By re-ordering wire sequences based on semantic meanings, we facilitate seamless semantic integration during sequence generation. Our two-phase technique merges a graph-based autoencoder with a transformer-based decoder to learn latent geometric tokens and generate semantic-aware wireframes. Through iterative prediction and decoding during inference, our model produces detailed wireframes that can be easily segmented into distinct components, such as walls, roofs, and rooms, reflecting the semantic essence of the shape. Empirical results on a comprehensive house dataset validate the superior accuracy, novelty, and semantic fidelity of our model compared to existing generative models. More results and details can be found on https://vcc.tech/research/2024/3DWire.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

42 of 55 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2020Longformer: The Long-Document Transformercited by 3,413
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  6. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  8. 2015Pointer Networkscited by 895
  9. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  10. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  11. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  12. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
30 more
  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  2. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  3. 2020Efficient Content-Based Sparse Attention with Routing Transformerscited by 471
  4. 2020A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospectscited by 397
  5. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  6. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 269
  7. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  8. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  9. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  10. 2020House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generationcited by 87
  11. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 80
  12. 2022HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoisingcited by 73
  13. 2019End-to-End Wireframe Parsingcited by 72
  14. 2020Learning to Parse Wireframes in Images of Man-Made Environmentscited by 71
  15. 2022DeepLSD: Line Segment Detection and Refinement with Deep Image Gradientscited by 60
  16. 2018Learning Attraction Field Representation for Robust Line Segment Detectioncited by 52
  17. 2022Connecting the Dots: Floorplan Reconstruction Using Two-Level Queriescited by 49
  18. 2020Deep Hough-Transform Line Priorscited by 44
  19. 2021Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequencescited by 39
  20. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  21. 2019Learning to Reconstruct 3D Manhattan Wireframes from a Single Imagecited by 35
  22. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  23. 2023Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulationcited by 27
  24. 2022Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learningcited by 26
  25. 2023Tell2Design: A Dataset for Language-Guided Floor Plan Generationcited by 19
  26. 2021ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Designcited by 12
  27. 2022HoW-3D: Holistic 3D Wireframe Perception from a Single Imagecited by 12
  28. 2020Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Onlycited by 10
  29. 2022Learning to Construct 3D Building Wireframes from 3D Line Cloudscited by 9
  30. 20213D Parametric Wireframe Extraction Based on Distance Fieldscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generationcited by 13
  2. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 13
  3. 2026MeshTailor: Cutting Seams via Generative Mesh Traversalcited by 4
  4. 2025SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learningcited by 2
  5. 2025SYNBUILD-3D: A large, multi-modal, and semantically rich synthetic dataset of 3D building models at Level of Detail 4cited by 0
  6. 2026FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printingcited by 0
  7. 2026SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Videocited by 0
  8. 2026GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusioncited by 0