# 4D Gaussian Splatting SLAM

arXiv: https://arxiv.org/abs/2503.16710 · HTML: https://mlsanity.com/paper/2503.16710/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 30 of 35)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM](https://mlsanity.com/paper/2312.02126/) (2023)
- [SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes](https://mlsanity.com/paper/2312.14937/) (2023)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields](https://mlsanity.com/paper/2210.13641/) (2022)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos](https://mlsanity.com/paper/2403.01444/) (2024)
- [Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting](https://mlsanity.com/paper/2312.10070/) (2023)
- [Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2404.03613/) (2024)
- [RobustNeRF: Ignoring Distractors with Robust Losses](https://mlsanity.com/paper/2302.00833/) (2023)
- [DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments](https://mlsanity.com/paper/1809.08379/) (2018)
- [GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering](https://mlsanity.com/paper/2403.11324/) (2024)
- [PPGNet: Learning Point-Pair Graph for Line Segment Detection](https://mlsanity.com/paper/1905.03415/) (2019)
- [DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization](https://mlsanity.com/paper/2411.08373/) (2024)
- [Dynamic SLAM: The Need For Speed](https://mlsanity.com/paper/2002.08584/) (2020)
- [Structure-SLAM: Low-Drift Monocular SLAM in Indoor Environments](https://mlsanity.com/paper/2008.01963/) (2020)
- [RoDyn-SLAM: Robust Dynamic Dense RGB-D SLAM with Neural Radiance Fields](https://mlsanity.com/paper/2407.01303/) (2024)

## Built on by (most cited first, 10 of 10)

- [DROID-SLAM in the Wild](https://mlsanity.com/paper/2603.19076/) (2026)
- [SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2511.17207/) (2025)
- [NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting](https://mlsanity.com/paper/2602.17182/) (2026)
- [Benchmarking PhD-Level Coding in 3D Geometric Computer Vision](https://mlsanity.com/paper/2603.30038/) (2026)
- [4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting](https://mlsanity.com/paper/2608.25956/) (2026)
- [ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos](https://mlsanity.com/paper/2509.17864/) (2025)
- [Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale](https://mlsanity.com/paper/2510.01665/) (2025)
- [RU4D-SLAM: Reweighting Uncertainty in Gaussian Splatting SLAM for 4D Scene Reconstruction](https://mlsanity.com/paper/2602.20807/) (2026)
- [Stitch4D: Sparse Multi-Location 4D Urban Reconstruction via Spatio-Temporal Interpolation](https://mlsanity.com/paper/2604.07923/) (2026)
- [Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluation](https://mlsanity.com/paper/2609.33872/) (2026)

## Abstract (arXiv)

Simultaneously localizing camera poses and constructing Gaussian radiance fields in dynamic scenes establish a crucial bridge between 2D images and the 4D real world. Instead of removing dynamic objects as distractors and reconstructing only static environments, this paper proposes an efficient architecture that incrementally tracks camera poses and establishes the 4D Gaussian radiance fields in unknown scenarios by using a sequence of RGB-D images. First, by generating motion masks, we obtain static and dynamic priors for each pixel. To eliminate the influence of static scenes and improve the efficiency on learning the motion of dynamic objects, we classify the Gaussian primitives into static and dynamic Gaussian sets, while the sparse control points along with an MLP is utilized to model the transformation fields of the dynamic Gaussians. To more accurately learn the motion of dynamic Gaussians, a novel 2D optical flow map reconstruction algorithm is designed to render optical flows of dynamic objects between neighbor images, which are further used to supervise the 4D Gaussian radiance fields along with traditional photometric and geometric constraints. In experiments, qualitative and quantitative evaluation results show that the proposed method achieves robust tracking and high-quality view synthesis performance in real-world environments.