Research map / Detection and segmentation / Open-set and few-shot detection
EM-Fusion: Dynamic Object-Level SLAM With Probabilistic Data Association
Michael Strecke, Jorg Stuckler
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 association likelihoods in tracking and mapping (ablation) | EM-Fusion · Co-Fusion Room4 Horse | AT-RMSE (cm): 9.12 -> 3.57 | Improved |
| add map confidence weights in tracking (ablation) | EM-Fusion · Co-Fusion Room4 Horse | AT-RMSE (cm): 8.38 -> 3.57 | Improved |
| add association likelihoods in tracking and mapping (ablation) | EM-Fusion · Co-Fusion Room4 Static Bg | AT-RMSE (cm): 1.42 -> 1.37 | Improved |
| add association likelihoods in tracking and mapping (ablation) | EM-Fusion · Co-Fusion Room4 Car | AT-RMSE (cm): 2.01 -> 2.10 | No clear effect |
| add map confidence weights in tracking (ablation) | EM-Fusion · Co-Fusion Room4 Car | AT-RMSE (cm): 2.11 -> 2.10 | No clear effect |
| add map confidence weights in tracking (ablation) | EM-Fusion · Co-Fusion Room4 Static Bg | AT-RMSE (cm): 1.37 -> 1.37 | No clear effect |
| use robust direct SDF alignment with Huber norm instead of ICP without robust norm (EM-Fusion vs MF) | EM-Fusion · Co-Fusion ToyCar3 Static Bg | AT-RMSE (cm): 20.60 -> 0.95 | Improved |
| EM-Fusion versus MaskFusion on the teddy bear trajectory | EM-Fusion · TUM f3_long_office_household teddy | AT-RMSE (cm): 2.2 -> 3.5 | Hurt |
| EM-Fusion versus MaskFusion on camera trajectory | EM-Fusion · TUM f3_long_office_household camera | AT-RMSE (cm): 8.9 -> 5.0 | Improved |
Closest papers by meaning
- DROID-SLAM in the Wild (CVPR 2026 · similarity 0.87)
- RGB-D SLAM in Dynamic Environments Using Point Correlations (TPAMI 2020 · similarity 0.86)
- CTO-SLAM: Contour Tracking for Object-Level Robust 4D SLAM (AAAI 2024 · similarity 0.86)
- WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 2025 · similarity 0.86)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.84)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.84)
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.
