# Robust Dense Mapping for Large-Scale Dynamic Environments

arXiv: https://arxiv.org/abs/1905.02781 · HTML: https://mlsanity.com/paper/1905.02781/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2019.

## Built on by (most cited first, 21 of 21)

- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild](https://mlsanity.com/paper/2207.09137/) (2022)
- [NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild](https://mlsanity.com/paper/2405.18715/) (2024)
- [STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer](https://mlsanity.com/paper/2508.10893/) (2025)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)
- [SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2312.13308/) (2023)
- [BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking](https://mlsanity.com/paper/2205.02301/) (2022)
- [4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere](https://mlsanity.com/paper/2602.10094/) (2026)
- [AirDOS: Dynamic SLAM benefits from Articulated Objects](https://mlsanity.com/paper/2109.09903/) (2021)
- [MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation](https://mlsanity.com/paper/2210.02038/) (2022)
- [3D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representation](https://mlsanity.com/paper/2405.03388/) (2024)
- [Semantic Visual Simultaneous Localization and Mapping: A Survey](https://mlsanity.com/paper/2209.06428/) (2022)
- [TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction](https://mlsanity.com/paper/2105.07468/) (2021)
- [Comparison of modern open-source visual SLAM approaches](https://mlsanity.com/paper/2108.01654/) (2021)
- [Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference](https://mlsanity.com/paper/2108.03180/) (2021)
- [GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System](https://mlsanity.com/paper/2408.09191/) (2024)
- [FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry](https://mlsanity.com/paper/2603.07690/) (2026)
- [Learning Multi-frame and Monocular Prior for Estimating Geometry in Dynamic Scenes](https://mlsanity.com/paper/2505.01737/) (2025)
- [3 Dimensional Dense Reconstruction: A Review of Algorithms and Dataset](https://mlsanity.com/paper/2304.09371/) (2023)
- [3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction](https://mlsanity.com/paper/2503.12001/) (2025)

## Abstract (arXiv)

We present a stereo-based dense mapping algorithm for large-scale dynamic urban environments. In contrast to other existing methods, we simultaneously reconstruct the static background, the moving objects, and the potentially moving but currently stationary objects separately, which is desirable for high-level mobile robotic tasks such as path planning in crowded environments. We use both instance-aware semantic segmentation and sparse scene flow to classify objects as either background, moving, or potentially moving, thereby ensuring that the system is able to model objects with the potential to transition from static to dynamic, such as parked cars. Given camera poses estimated from visual odometry, both the background and the (potentially) moving objects are reconstructed separately by fusing the depth maps computed from the stereo input. In addition to visual odometry, sparse scene flow is also used to estimate the 3D motions of the detected moving objects, in order to reconstruct them accurately. A map pruning technique is further developed to improve reconstruction accuracy and reduce memory consumption, leading to increased scalability. We evaluate our system thoroughly on the well-known KITTI dataset. Our system is capable of running on a PC at approximately 2.5Hz, with the primary bottleneck being the instance-aware semantic segmentation, which is a limitation we hope to address in future work. The source code is available from the project website (http://andreibarsan.github.io/dynslam).