Research map / 3D vision / Gaussian splatting
RoomPlanner: Reachability-Aware View Sampling for Text-to-Room 3D Gaussian Splatting
Wenzhuo Sun, MingJian Liang, Wenxuan Song, Xuelian Cheng, Zongyuan Ge
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 ITFS and ReachView (vs conventional cameras with SDS) (ablation) | RoomPlanner · Indoor scene rendering (bedroom, living room) | visual quality | Improved |
| add ReachView camera sampling to ITFS (ablation) | RoomPlanner · Indoor scene rendering (bedroom, living room) | geometric stability and detail | Improved |
| add reachability constraint to layout arrangement (vs LayoutVLM) | RoomPlanner · Layout quality | colliding object pairs: 11.09 -> 0.00 | Improved |
| add reachability constraint to layout arrangement (vs LayoutVLM) | RoomPlanner · Layout quality | reachable objects %: 86.2 -> 100.0 | Improved |
| add reachability constraint (vs Holodeck) | RoomPlanner · Layout quality | out-of-bounds objects: 0.87 -> 0.20 | Improved |
| add reachability constraint (vs Holodeck) | RoomPlanner · Layout quality | reachable objects %: 97.3 -> 100.0 | Improved |
| use RoomPlanner instead of DreamScene | RoomPlanner · Indoor scene generation (user study) | Rationality: 3.10 -> 4.10 | Improved |
| use RoomPlanner instead of DreamScene | RoomPlanner · Indoor scene generation (automatic) | CLIP Score %: 26.77 -> 28.44 | Improved |
| use RoomPlanner instead of DreamScene | RoomPlanner · Indoor scene generation (automatic) | ImageReward: 43.85 -> 48.83 | Improved |
| add collision constraint (vs Holodeck) | RoomPlanner · Layout quality | colliding object pairs: 0.00 -> 0.00 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GALA3D — GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting (ICML 2024) · better on 5 of 5 shared results
- DreamScene — DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling (ECCV 2024) · better on 5 of 5 shared results
- Holodeck — Holodeck: Language Guided Generation of 3D Embodied AI Environments (CVPR 2024) · better on 2 of 3 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
- SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs (CVPR 2025 · similarity 0.88)
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR 2024 · similarity 0.87)
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.87)
- DeBaRA: Denoising-Based 3D Room Arrangement Generation (NeurIPS 2024 · similarity 0.87)
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent (NeurIPS 2025 · similarity 0.87)
- PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors (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.
