Research map / 3D vision / 3D generation
WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion
Manuel-Andreas Schneider, Angela Dai
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 textured wall projection to depth+objects conditioning (ablation) | WorldMesh · Gothic scene user study | Quality (1-5): 3.35 -> 4.48 | Improved |
| Use reconstructed objects instead of bounding boxes (ablation) | WorldMesh · Gothic scene user study | Quality (1-5): 2.19 -> 4.48 | Improved |
| Add mesh scaffold objects and walls to depth-only conditioning (ablation) | WorldMesh · Gothic scene user study | Quality (1-5): 2.10 -> 4.48 | Improved |
| Add mesh depth loss to 3DGS optimization (ablation) | WorldMesh · 5 multi-room scenes | Reproj MAE-norm: 0.3009 -> 0.1615 | Improved |
| Add mesh point-cloud init and depth loss together (ablation) | WorldMesh · 5 multi-room scenes | Reproj MAE-norm: 1.8804 -> 0.1615 | Improved |
| Add edge-recall validation of generated images (ablation) | WorldMesh · 5 multi-room scenes | Reproj MAE-norm: 0.1660 -> 0.1615 | Improved |
| Use Nano Banana Pro instead of local Flux2-klein-9B (ablation) | WorldMesh · 5 multi-room scenes | Reproj MAE-norm: 0.2173 -> 0.1615 | Improved |
| Scale from 4 to 12 rooms | WorldMesh · Per-scene scaling | Reproj MAE-norm: 0.11 -> 0.23 | Mixed |
| Replace baselines with WorldMesh | WorldMesh · Pairwise user study | preference: 96.2% average | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DreamScene360 — DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting (ECCV 2024) · better on 3 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
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (CVPR 2024 · similarity 0.89)
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (ICLR 2024 · similarity 0.88)
- Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting (NeurIPS 2024 · similarity 0.88)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · similarity 0.88)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.88)
- PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models (CVPR 2025 · similarity 0.88)
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.
