Research map / 3D vision / 3D generation
One Video, One World: Turning Monocular Video into Physical 4D Scenes
Junhao Chen, Boran Zhang, Mingjin Chen, Henghaofan Zhang, Saining Zhang, Congcong Zhu, HAO ZHAO, Ruqi Huang, Zhihao Li, Yufei Wang
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 |
|---|---|---|---|
| increase refinement iterations from 1 to 3 (ablation) | OVOW · validation set | IoU-B: 0.58 -> 0.78 | Improved |
| increase refinement iterations from 3 to 5 (ablation) | OVOW · validation set | IoU-B: 0.78 -> 0.79 | No clear effect |
| set rho to 0.65 instead of 0.55 (ablation) | OVOW · validation set | IoU-B: 0.74 -> 0.78 | Improved |
| raise rho from 0.65 to 0.75 (ablation) | OVOW · validation set | IoU-B: 0.78 -> 0.76 | Hurt |
| set tau_area to 200 instead of 100 (ablation) | OVOW · validation set | Valid scenes: 84.9 -> 86.8 | Improved |
| raise tau_area from 200 to 400 (ablation) | OVOW · validation set | Valid scenes: 86.8 -> 85.7 | Hurt |
| set tau_contact to 3% instead of 2% (ablation) | OVOW · validation set | Sim. stability: 79.8 -> 82.7 | Improved |
| raise tau_contact from 3% to 4% (ablation) | OVOW · validation set | Sim. stability: 82.7 -> 81.5 | Hurt |
| use 2 assembly rounds instead of 1 (ablation) | OVOW · validation set | Sim. stability: 78.9 -> 82.7 | Improved |
| use 5 assembly rounds instead of 2 (ablation) | OVOW · validation set | Sim. stability: 82.7 -> 82.8 | No clear effect |
| use video input (OVOW) instead of per-frame image baseline MIDI | OVOW · OVOW-4D-Scene-Bench | Scene-IoU OBB: 0.198 -> 0.440 | Improved |
| use video input (OVOW) instead of per-frame image baseline MIDI | OVOW · OVOW-4D-Scene-Bench | Time (s/frame): 234 -> 3.35 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- SAM3D — SAM 3D: 3Dfy Anything in Images (CVPR 2026) · better on 5 of 5 shared results
- TabletopGen — TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation (ECCV 2026) · better on 5 of 5 shared results
- MIDI — MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation (CVPR 2025) · better on 5 of 5 shared results
- SceneGen — SceneGen: Learning To Generate Realistic Traffic Scenes (CVPR 2021) · better on 5 of 5 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
- MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos (NeurIPS 2026 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time (NeurIPS 2025 · similarity 0.87)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.87)
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video (NeurIPS 2025 · similarity 0.87)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 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.
