# MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM

arXiv: https://arxiv.org/abs/1812.07976 · HTML: https://mlsanity.com/paper/1812.07976/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2018.

## Built on by (most cited first, 30 of 65)

- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](https://mlsanity.com/paper/2303.14158/) (2023)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models](https://mlsanity.com/paper/2108.00516/) (2021)
- [SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition](https://mlsanity.com/paper/2106.03849/) (2021)
- [vMAP: Vectorised Object Mapping for Neural Field SLAM](https://mlsanity.com/paper/2302.01838/) (2023)
- [Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems](https://mlsanity.com/paper/2106.14386/) (2021)
- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [Continuous Scene Representations for Embodied AI](https://mlsanity.com/paper/2203.17251/) (2022)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [Audio Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2303.07522/) (2023)
- [DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments](https://mlsanity.com/paper/2209.08430/) (2022)
- [PVO: Panoptic Visual Odometry](https://mlsanity.com/paper/2207.01610/) (2022)
- [BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking](https://mlsanity.com/paper/2205.02301/) (2022)
- [RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration](https://mlsanity.com/paper/2504.06994/) (2025)
- [Regularized Deep Signed Distance Fields for Reactive Motion Generation](https://mlsanity.com/paper/2203.04739/) (2022)
- [NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping](https://mlsanity.com/paper/2303.07308/) (2023)
- [Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2411.19162/) (2024)
- [Online Language Splatting](https://mlsanity.com/paper/2503.09447/) (2025)
- [Learning to Complete Object Shapes for Object-level Mapping in Dynamic Scenes](https://mlsanity.com/paper/2208.05067/) (2022)
- [MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation](https://mlsanity.com/paper/2210.02038/) (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)
- [DVN-SLAM: Dynamic Visual Neural SLAM Based on Local-Global Encoding](https://mlsanity.com/paper/2403.11776/) (2024)
- [Multimodal Spatial Language Maps for Robot Navigation and Manipulation](https://mlsanity.com/paper/2506.06862/) (2025)
- [Perceiving Unseen 3D Objects by Poking the Objects](https://mlsanity.com/paper/2302.13375/) (2023)
- [Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors](https://mlsanity.com/paper/2410.05514/) (2024)
- [SegMASt3R: Geometry Grounded Segment Matching](https://mlsanity.com/paper/2510.05051/) (2025)

## Abstract (arXiv)

We propose a new multi-instance dynamic RGB-D SLAM system using an object-level octree-based volumetric representation. It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the scene. For each incoming frame, we perform instance segmentation to detect objects and refine mask boundaries using geometric and motion information. Meanwhile, we estimate the pose of each existing moving object using an object-oriented tracking method and robustly track the camera pose against the static scene. Based on the estimated camera pose and object poses, we associate segmented masks with existing models and incrementally fuse corresponding colour, depth, semantic, and foreground object probabilities into each object model. In contrast to existing approaches, our system is the first system to generate an object-level dynamic volumetric map from a single RGB-D camera, which can be used directly for robotic tasks. Our method can run at 2-3 Hz on a CPU, excluding the instance segmentation part. We demonstrate its effectiveness by quantitatively and qualitatively testing it on both synthetic and real-world sequences.