Research map / 3D vision / Face and shape
Generating 3D House Wireframes with Semantics
Xueqi Ma, Yilin Liu, Wenjun Zhou, Ruowei Wang, Hui Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LMH attention layers to the autoencoder encoder (ablation) | 3D wireframe autoencoder · 3D house wireframe dataset | COV: 49.07 -> 56.15 | Improved |
| use Residual LFQ instead of VQ for the geometric codebook (ablation) | 3D wireframe autoencoder · 3D house wireframe dataset | COV: 50.02 -> 56.15 | Improved |
| add coarse-to-fine decoding in the transformer (ablation) | 3D wireframe transformer · 3D house wireframe dataset | COV: 52.56 -> 56.15 | Improved |
| reorder training sequences by semantic order instead of z-y-x sorting (ablation) | 3D wireframe transformer · 3D house wireframe dataset | COV: 51.33 -> 56.15 | Improved |
| add semantic order to training sequences (ablation) | 3D wireframe transformer · 3D house wireframe dataset | 3L-CVP (%): 67.69 -> 99.26 | Improved |
| use unified wire-based autoregressive generation instead of vertex-then-connection (PolyGen) | wireframe generator · 3D house wireframe dataset | 2L-CVP (%): 81.47 -> 99.53 | Improved |
| apply method to more diverse ABC planar shapes | wireframe generator · ABC subset | COV (%): 44.10 vs 42.38 (MeshGPT) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MeshGPT — MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024) · better on 6 of 6 shared results
- PolyGen — PolyGen: An Autoregressive Generative Model of 3D Meshes (ICML 2020) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Neural Wireframe Renderer: Learning Wireframe to Image Translations (ECCV 2020 · similarity 0.88)
- Intelligent Home 3D: Automatic 3D-House Design From Linguistic Descriptions Only (CVPR 2020 · similarity 0.88)
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.85)
- NEAT: Distilling 3D Wireframes from Neural Attraction Fields (CVPR 2024 · similarity 0.84)
- Wired Perspectives: Multi-View Wire Art Embraces Generative AI (CVPR 2024 · similarity 0.84)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
