Research map / 3D vision / 3D generation
SimRecon: SimReady Compositional Scene Reconstruction from Real Videos
Chong Xia, Kai Zhu, Zizhuo Wang, Fangfu Liu, Zhizheng Zhang, Yueqi Duan
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 |
|---|---|---|---|
| use active viewpoint optimization instead of max 2D visibility view selection (ablation) | SimRecon AVO · ScanNet kettle example | generated asset quality (qualitative) | Improved |
| add depth regularization L_depth to viewpoint optimization (ablation) | SimRecon AVO · ScanNet | viewpoint quality (qualitative) | Improved |
| use regional scene graph inference instead of a single global inference (ablation) | SimRecon SGS · ScanNet | scene graph quality (qualitative) | Improved |
| add conflict resolution to subgraph merging (ablation) | SimRecon SGS · ScanNet | scene graph coherence (qualitative) | Improved |
| use SimRecon instead of InstaScene | compositional reconstruction · ScanNet (20 scenes) | Chamfer Distance: 6.90 -> 4.34 | Improved |
| use SimRecon instead of InstaScene | compositional reconstruction · ScanNet (20 scenes) | F-Score: 49.69 -> 62.65 | Improved |
| use SimRecon instead of InstaScene | compositional reconstruction · ScanNet (20 scenes) | LPIPS: 0.302 -> 0.153 | Improved |
| use SimRecon instead of DPRecon | compositional reconstruction · ScanNet (20 scenes) | inference time: 10h 42min -> 21min | Improved |
| use SimRecon instead of SceneGen | compositional reconstruction · ScanNet (20 scenes) | inference time: 6min -> 21min | Hurt |
| use scene graph guided physical assembly instead of post-hoc MCMC collision search (MetaScenes) | simulation scene construction · ScanNet in Blender | physical plausibility (qualitative) | 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.
- SceneGen — SceneGen: Learning To Generate Realistic Traffic Scenes (CVPR 2021) · better on 7 of 7 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
- SimVS: Simulating World Inconsistencies for Robust View Synthesis (CVPR 2025 · similarity 0.88)
- Video Perception Models for 3D Scene Synthesis (NeurIPS 2025 · similarity 0.87)
- Compositional Scene Understanding through Inverse Generative Modeling (ICML 2025 · similarity 0.87)
- Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image (NeurIPS 2026 · similarity 0.86)
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.85)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.85)
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.
