Research map / 3D vision / 3D generation
FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes
Yuxi Wang, Junran Peng, Genghao Zhang, Chuanchen Luo, Shibiao Xu, Man Zhang, Zhaoxiang 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 positional encoding in first stage furniture list network (ablation) | TSDSM · FurniScene Living Room (w/o text) | FID: 44.45 -> 53.53 | Hurt |
| add positional encoding in first stage furniture list network (ablation) | TSDSM · FurniScene Living Room (w/ text) | FID: 36.54 -> 52.47 | Hurt |
| use multi-head transformer instead of single-head in second stage (ablation) | TSDSM · FurniScene Living Room (w/o text) | FID: 51.54 -> 44.45 | Improved |
| use multi-head transformer instead of single-head in second stage (ablation) | TSDSM · FurniScene Living Room (w/ text) | FID: 50.49 -> 36.54 | Improved |
| add separate MLPs per attribute in second stage (ablation) | TSDSM · FurniScene Living Room (w/o text) | FID: 100.10 -> 44.45 | Improved |
| add separate MLPs per attribute in second stage (ablation) | TSDSM · FurniScene Living Room (w/ text) | FID: 48.82 -> 36.54 | Improved |
| add separate MLPs per attribute in second stage (ablation) | TSDSM · FurniScene Living Room (w/o text) | CKL x0.001: 42.90 -> 38.30 | Improved |
| two-stage diffusion (TSDSM w/o text) instead of DiffuScene | DiffuScene · FurniScene Bedroom | FID: 110.00 -> 46.37 | Improved |
| two-stage diffusion (TSDSM w/o text) instead of ATISS | ATISS · FurniScene Bedroom | CKL x0.001: 10.18 -> 125.42 | Hurt |
| add text prompt conditioning to TSDSM | TSDSM · FurniScene Living Room | FID: 44.45 -> 36.54 | Improved |
| add text prompt conditioning to TSDSM | TSDSM · FurniScene Bedroom | FID: 46.37 -> 50.88 | Hurt |
| add text prompt conditioning to TSDSM | TSDSM · FurniScene Bedroom | CKL x0.001: 125.42 -> 53.44 | Improved |
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.
- ATISS — ATISS: Autoregressive Transformers for Indoor Scene Synthesis (NeurIPS 2021) · better on 7 of 7 shared results
- DiffuScene — DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis (CVPR 2024) · better on 6 of 6 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
- OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization (NeurIPS 2025 · similarity 0.89)
- SceneCraft: Layout-Guided 3D Scene Generation (NeurIPS 2024 · similarity 0.87)
- InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts (NeurIPS 2025 · similarity 0.87)
- DeBaRA: Denoising-Based 3D Room Arrangement Generation (NeurIPS 2024 · similarity 0.87)
- DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation (CVPR 2024 · similarity 0.87)
- ControlRoom3D: Room Generation using Semantic Proxy Rooms (CVPR 2024 · similarity 0.86)
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.
