Research map / 3D vision / 3D generation
Intelligent Home 3D: Automatic 3D-House Design From Linguistic Descriptions Only
Qi Chen, Qi Wu, Rui Tang, Yuhan Wang, Shuai Wang, Mingkui Tan
Check 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 |
|---|---|---|---|
| Use graph-conditioned layout prediction instead of manual rule-based layout generation | Text-to-3D House Model · Text-to-3D House Model | IoU: 0.7208 -> 0.8348 | Improved |
| Use graph convolution to incorporate neighboring-room information (ablation) | GC-LPN · Text-to-3D House Model | IoU: 0.8037 -> 0.8348 | Improved |
| Use graph convolution rather than sequential LSTM layout prediction (ablation) | GC-LPN · Text-to-3D House Model | IoU: 0.7918 -> 0.8348 | Improved |
| Use LCT-GAN for conditional texture generation | Texture synthesis · Texture synthesis test set | FID: 220.18 -> 145.16 | Improved |
| Add the material-aware loss to adversarial and colour-aware training (ablation) | LCT-GAN · Texture synthesis test set | FID: 158.20 -> 145.16 | Improved |
| Add the colour-aware loss to adversarial and material-aware training (ablation) | LCT-GAN · Texture synthesis test set | FID: 157.01 -> 145.16 | Improved |
| Add the material-aware loss to adversarial and colour-aware training (ablation) | LCT-GAN · Texture synthesis test set | MS-SSIM: 0.4263 -> 0.3859 | Improved |
| Add the colour-aware loss to adversarial and material-aware training (ablation) | LCT-GAN · Texture synthesis test set | MS-SSIM: 0.4191 -> 0.3859 | Improved |
| Add both material-aware and colour-aware losses to adversarial training (ablation) | LCT-GAN · Texture synthesis | controllability | Improved |
Closest papers by meaning
- Nestwork: Conditional 3D Furnished House Layout Generation through Latent Heterogeneous Graph Diffusion (CVPR 2026 · similarity 0.90)
- HouseTune: Two-Stage Floorplan Generation with LLM Assistance (AAAI 2026 · similarity 0.89)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.87)
- Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans (CVPR 2026 · similarity 0.86)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · similarity 0.86)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.85)
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.
