# FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow

arXiv: https://arxiv.org/abs/2003.05102 · HTML: https://mlsanity.com/paper/2003.05102/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 30 of 37)

- [WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments](https://mlsanity.com/paper/2504.03886/) (2025)
- [DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments](https://mlsanity.com/paper/2209.08430/) (2022)
- [RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2309.15082/) (2023)
- [DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM](https://mlsanity.com/paper/2401.01545/) (2024)
- [MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction](https://mlsanity.com/paper/2402.03762/) (2024)
- [AKiRa: Augmentation Kit on Rays for optical video generation](https://mlsanity.com/paper/2412.14158/) (2024)
- [SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering](https://mlsanity.com/paper/2108.00454/) (2021)
- [A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow](https://mlsanity.com/paper/2203.13214/) (2022)
- [Neuromorphic Optical Flow and Real-time Implementation with Event Cameras](https://mlsanity.com/paper/2304.07139/) (2023)
- [PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments](https://mlsanity.com/paper/2411.15800/) (2024)
- [DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes](https://mlsanity.com/paper/2503.11979/) (2025)
- [DROID-SLAM in the Wild](https://mlsanity.com/paper/2603.19076/) (2026)
- [D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance](https://mlsanity.com/paper/2207.08794/) (2022)
- [Context-PIPs: Persistent Independent Particles Demands Spatial Context Features](https://mlsanity.com/paper/2306.02000/) (2023)
- [Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images](https://mlsanity.com/paper/2506.07740/) (2025)
- [MPI-Flow: Learning Realistic Optical Flow with Multiplane Images](https://mlsanity.com/paper/2309.06714/) (2023)
- [RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting](https://mlsanity.com/paper/2412.01217/) (2024)
- [Perception for Humanoid Robots](https://mlsanity.com/paper/2309.15616/) (2023)
- [Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments](https://mlsanity.com/paper/2506.05965/) (2025)
- [Attentive Multimodal Fusion for Optical and Scene Flow](https://mlsanity.com/paper/2307.15301/) (2023)
- [Camera Motion Estimation from RGB-D-Inertial Scene Flow](https://mlsanity.com/paper/2404.17251/) (2024)
- [Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments](https://mlsanity.com/paper/2602.21967/) (2026)
- [AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments](https://mlsanity.com/paper/2108.01246/) (2021)
- [NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU](https://mlsanity.com/paper/2405.07392/) (2024)
- [BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding](https://mlsanity.com/paper/2412.02449/) (2024)
- [Embracing Dynamics: Dynamics-aware 4D Gaussian Splatting SLAM](https://mlsanity.com/paper/2504.04844/) (2025)
- [SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos](https://mlsanity.com/paper/2504.17810/) (2025)
- [Optical Flow-Guided 6DoF Object Pose Tracking with an Event Camera](https://mlsanity.com/paper/2512.21053/) (2025)
- [CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping](https://mlsanity.com/paper/2505.19420/) (2025)
- [ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos](https://mlsanity.com/paper/2509.17864/) (2025)

## Abstract (arXiv)

Dynamic environments are challenging for visual SLAM since the moving objects occlude the static environment features and lead to wrong camera motion estimation. In this paper, we present a novel dense RGB-D SLAM solution that simultaneously accomplishes the dynamic/static segmentation and camera ego-motion estimation as well as the static background reconstructions. Our novelty is using optical flow residuals to highlight the dynamic semantics in the RGB-D point clouds and provide more accurate and efficient dynamic/static segmentation for camera tracking and background reconstruction. The dense reconstruction results on public datasets and real dynamic scenes indicate that the proposed approach achieved accurate and efficient performances in both dynamic and static environments compared to state-of-the-art approaches.