# EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association

arXiv: https://arxiv.org/abs/1904.11781 · HTML: https://mlsanity.com/paper/1904.11781/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2019.

## Built on by (most cited first, 28 of 28)

- [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](https://mlsanity.com/paper/2303.14158/) (2023)
- [BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models](https://mlsanity.com/paper/2108.00516/) (2021)
- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)
- [Continuous Scene Representations for Embodied AI](https://mlsanity.com/paper/2203.17251/) (2022)
- [DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM](https://mlsanity.com/paper/2401.01545/) (2024)
- [An Object SLAM Framework for Association, Mapping, and High-Level Tasks](https://mlsanity.com/paper/2305.07299/) (2023)
- [NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping](https://mlsanity.com/paper/2303.07308/) (2023)
- [D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance](https://mlsanity.com/paper/2207.08794/) (2022)
- [Learning to Complete Object Shapes for Object-level Mapping in Dynamic Scenes](https://mlsanity.com/paper/2208.05067/) (2022)
- [SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning](https://mlsanity.com/paper/2208.08307/) (2022)
- [Semantic Visual Simultaneous Localization and Mapping: A Survey](https://mlsanity.com/paper/2209.06428/) (2022)
- [Neural Implicit Vision-Language Feature Fields](https://mlsanity.com/paper/2303.10962/) (2023)
- [UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments](https://mlsanity.com/paper/2505.22335/) (2025)
- [TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction](https://mlsanity.com/paper/2105.07468/) (2021)
- [Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference](https://mlsanity.com/paper/2108.03180/) (2021)
- [Factored Neural Representation for Scene Understanding](https://mlsanity.com/paper/2304.10950/) (2023)
- [Learning-based Relational Object Matching Across Views](https://mlsanity.com/paper/2305.02398/) (2023)
- [Physics-Based Rigid Body Object Tracking and Friction Filtering From RGB-D Videos](https://mlsanity.com/paper/2309.15703/) (2023)
- [Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation](https://mlsanity.com/paper/2208.04274/) (2022)
- [TivNe-SLAM: Dynamic Mapping and Tracking via Time-Varying Neural Radiance Fields](https://mlsanity.com/paper/2310.18917/) (2023)
- [OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects](https://mlsanity.com/paper/2510.20605/) (2025)
- [Superquadric Object Representation for Optimization-based Semantic SLAM](https://mlsanity.com/paper/2109.09627/) (2021)
- [3D Multi-Object Tracking with Differentiable Pose Estimation](https://mlsanity.com/paper/2206.13785/) (2022)
- [Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments](https://mlsanity.com/paper/2211.14310/) (2022)
- [ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification](https://mlsanity.com/paper/2311.02734/) (2023)
- [MoPe: Motion Permanence for Robust Monocular Gaussian Mapping in Dynamic Environments](https://mlsanity.com/paper/2606.29237/) (2026)
- [PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation](https://mlsanity.com/paper/2607.07170/) (2026)
- [RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos](https://mlsanity.com/paper/2608.29003/) (2026)

## Abstract (arXiv)

The majority of approaches for acquiring dense 3D environment maps with RGB-D cameras assumes static environments or rejects moving objects as outliers. The representation and tracking of moving objects, however, has significant potential for applications in robotics or augmented reality. In this paper, we propose a novel approach to dynamic SLAM with dense object-level representations. We represent rigid objects in local volumetric signed distance function (SDF) maps, and formulate multi-object tracking as direct alignment of RGB-D images with the SDF representations. Our main novelty is a probabilistic formulation which naturally leads to strategies for data association and occlusion handling. We analyze our approach in experiments and demonstrate that our approach compares favorably with the state-of-the-art methods in terms of robustness and accuracy.