Research map / 3D vision / Gaussian splatting
Space-Time Localization and Mapping
Minhaeng Lee, Charless C. Fowlkes
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 |
|---|---|---|---|
| model temporal extent and visibility (4D model) instead of a single 3D reconstruction | ElasticFusion on concatenated data · Synthetic 4D benchmark | precision: 71.3% -> 93.3% | Improved |
| add temporal extent and visibility reasoning on top of per-time alignment | EF4D · Synthetic 4D benchmark | recall: 90.0% -> 98.5% | Improved |
| add temporal extent and visibility reasoning on top of per-time alignment | EF4D · Synthetic 4D benchmark | precision: 92.7% -> 93.3% | Improved |
| model existence intervals instead of assuming all objects exist at all times | ST-SLAM · Synthetic Bedroom | temporal accuracy: 83.2% -> 90.8% | Improved |
| model existence intervals (non-static components only) | ST-SLAM · Synthetic Bedroom (NS) | temporal accuracy: 41.2% -> 74.3% | Improved |
| model existence intervals instead of assuming all objects exist at all times | ST-SLAM · Synthetic Bathroom | temporal accuracy: 69.7% -> 78.0% | Improved |
| model existence intervals (non-static components only) | ST-SLAM · Synthetic Bathroom (NS) | temporal accuracy: 31.8% -> 62.2% | Improved |
| add Dirichlet process growth of mixture components (ablation) | ST-SLAM · Synthetic Bedroom | temporal accuracy: 90.8% -> 90.9% | No clear effect |
| add Dirichlet process growth of mixture components (ablation) | ST-SLAM · Synthetic Bathroom | temporal accuracy: 78.0% -> 77.7% | Mixed |
| add visibility inference and DP mixtures under low scan overlap (ablation) | ST-SLAM versus ICP and JRMPC · Laboratory partial overlap registration | closest point distance | Improved |
| increase number of clusters beyond a certain point (ablation) | temporal segmentation · Copier room and Kitchen | segmentation accuracy | Hurt |
Closest papers by meaning
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 2025 · similarity 0.88)
- Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments (CVPR 2024 · similarity 0.87)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.86)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.86)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.86)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.86)
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.
