Research map / 3D vision / 3D generation
One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image
Pengfei Wang, Liyi Chen, Zhiyuan Ma, Yanjun Guo, Guowen Zhang, Lei 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 Dual-LoRA training instead of naive concatenation (ablation) | scaffold-guided NVS · WorldScore-adapted 40 scenes | CamMC: 0.655 -> 0.401 | Improved |
| add Dual-LoRA training instead of naive concatenation (ablation) | scaffold-guided NVS · WorldScore-adapted 40 scenes | CLIP-I: 85.30 -> 89.51 | Improved |
| add memory condition at inference (ablation) | Dual-LoRA NVS · WorldScore-adapted 40 scenes | CamMC: 0.401 -> 0.389 | Improved |
| add memory condition at inference (ablation) | Dual-LoRA NVS · WorldScore-adapted 40 scenes | NIQE: 4.42 -> 4.43 | No clear effect |
| add bidirectional fusion (BF) module (ablation) | panorama depth network · Matterport3D | AbsRel: 0.1204 -> 0.1070 | Improved |
| add bidirectional fusion (BF) module (ablation) | panorama depth network · Stanford2D3D | AbsRel: 0.0797 -> 0.0675 | Improved |
| replace AnySplat with the VGGT-based scaffold network | scene generation pipeline · WorldScore-adapted 40 scenes | CamMC: 0.616 -> 0.389 | Improved |
| replace AnySplat with the VGGT-based scaffold network | scene generation pipeline · WorldScore-adapted 40 scenes | Q-Align: 3.61 -> 4.13 | Improved |
| condition SEVA on anchor views | SEVA · WorldScore-adapted 40 scenes | CamMC: 0.558 -> 0.460 | Improved |
| condition VMem on anchor views | VMem · WorldScore-adapted 40 scenes | CamMC: 0.998 -> 0.887 | Improved |
| condition VMem on anchor views | VMem · WorldScore-adapted 40 scenes | TransErr: 0.573 -> 0.613 | Hurt |
| fine-tune on target panorama datasets | feed-forward 3DGS depth · Matterport3D | AbsRel: 0.1070 -> 0.0391 | 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.
- MVSplat360 — MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024) · better on 2 of 2 shared results
- HRDFuse — HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions (CVPR 2023) · better on 1 of 1 shared result
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
- Wonderland: Navigating 3D Scenes from a Single Image (CVPR 2025 · similarity 0.88)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.88)
- Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration (CVPR 2025 · similarity 0.87)
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (CVPR 2024 · similarity 0.87)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.87)
- MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation (CVPR 2024 · 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.
