Research map / 3D vision / 3D generation
3D-FRONT: 3D Furnished Rooms With layOuts and semaNTics
Huan Fu, Bowen Cai, Lin Gao, Ling-Xiao Zhang, Jiaming Wang, Cao Li, Qixun Zeng, Chengyue Sun, Rongfei Jia, Binqiang Zhao, Hao Zhang
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 graph auto-encoder (GAE) to primary ranking | FSC · Homestyler 8,000 scene designs (recommendation) | AUC: 0.766 -> 0.772 | Improved |
| add graph auto-encoder (GAE) to primary ranking | FSC · Homestyler 8,000 scene designs (recommendation) | 1-N Hit@10: 33.6% -> 36.1% | Improved |
| add graph auto-encoder (GAE) to primary ranking | FSC · Homestyler 8,000 scene designs (recommendation) | 1-N Hit@20: 61.3% -> 64.3% | Improved |
| add graph auto-encoder (GAE) to primary ranking | FSC · Homestyler 8,000 scene designs (recommendation) | 1-N Avg Rank: 41.6 -> 37.3 | Improved |
| add graph auto-encoder (GAE) to primary ranking | FSC · Homestyler 8,000 scene designs (recommendation) | N-1 Avg Rank: 26.7 -> 24.1 | Improved |
| train scene synthesis on 3D-FRONT instead of SUNCG | Wang et al. scene synthesis · Scene synthesis, combined test set | MMD-CD: 0.3642 -> 0.3371 | Improved |
| train scene synthesis on 3D-FRONT instead of SUNCG | Wang et al. scene synthesis · Scene synthesis, combined test set | MMD-EMD: 1.1490 -> 1.1049 | Improved |
| train scene synthesis on 3D-FRONT instead of SUNCG | Wang et al. scene synthesis · Scene synthesis, combined test set | COV-CD: 45.65 -> 50.01 | Improved |
| train scene synthesis on 3D-FRONT instead of SUNCG | Wang et al. scene synthesis · Scene synthesis, combined test set | COV-EMD: 46.72 -> 52.91 | Improved |
| train scene synthesis on 3D-FRONT instead of SUNCG | Wang et al. scene synthesis · Scene synthesis plausibility user study | % chosen as more plausible: 35.2% -> 64.8% | Improved |
| train TM-Net on 3D-FRONT instead of ShapeNet | TM-Net · Chair texture synthesis, dining rooms | LPIPS (diversity): 0.215 -> 0.289 | Improved |
| train TM-Net on 3D-FRONT instead of ShapeNet | TM-Net · Texture synthesis richness user study | % chosen as richer: 38.9% -> 61.1% | Improved |
Closest papers by meaning
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.89)
- ControlRoom3D: Room Generation using Semantic Proxy Rooms (CVPR 2024 · similarity 0.88)
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · similarity 0.88)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.88)
- DeBaRA: Denoising-Based 3D Room Arrangement Generation (NeurIPS 2024 · similarity 0.87)
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.87)
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.
