# 6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model

arXiv: https://arxiv.org/abs/2407.15484 · HTML: https://mlsanity.com/paper/2407.15484/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 28 of 28)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation](https://mlsanity.com/paper/2210.10108/) (2022)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation](https://mlsanity.com/paper/2101.12378/) (2021)
- [TransforMatcher: Match-to-Match Attention for Semantic Correspondence](https://mlsanity.com/paper/2205.11634/) (2022)
- [Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning](https://mlsanity.com/paper/1807.05933/) (2018)
- [Self-Supervised Equivariant Learning for Oriented Keypoint Detection](https://mlsanity.com/paper/2204.08613/) (2022)
- [Learning Rotation-Equivariant Features for Visual Correspondence](https://mlsanity.com/paper/2303.15472/) (2023)
- [VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis](https://mlsanity.com/paper/2205.15401/) (2022)
- [SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints](https://mlsanity.com/paper/2109.04884/) (2021)
- [Structure Aware SLAM using Quadrics and Planes](https://mlsanity.com/paper/1804.09111/) (2018)
- [OA-SLAM: Leveraging Objects for Camera Relocalization in Visual SLAM](https://mlsanity.com/paper/2209.08338/) (2022)
- [ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description](https://mlsanity.com/paper/2108.00355/) (2021)
- [Simultaneous Localisation and Mapping with Quadric Surfaces](https://mlsanity.com/paper/2203.08040/) (2022)
- [VERF: Runtime Monitoring of Pose Estimation with Neural Radiance Fields](https://mlsanity.com/paper/2308.05939/) (2023)
- [IFFNeRF: Initialisation Free and Fast 6DoF pose estimation from a single image and a NeRF model](https://mlsanity.com/paper/2403.12682/) (2024)
- [RGBD2lux: Dense light intensity estimation with an RGBD sensor](https://mlsanity.com/paper/1809.07558/) (2018)

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

- [GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2408.11085/) (2024)
- [What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models](https://mlsanity.com/paper/2512.03422/) (2025)
- [ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining](https://mlsanity.com/paper/2408.10906/) (2024)
- [From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting](https://mlsanity.com/paper/2503.19358/) (2025)
- [Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions](https://mlsanity.com/paper/2503.15898/) (2025)
- [LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling](https://mlsanity.com/paper/2507.02363/) (2025)
- [PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map](https://mlsanity.com/paper/2502.05752/) (2025)
- [Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization](https://mlsanity.com/paper/2507.23569/) (2025)
- [A Guide to Structureless Visual Localization](https://mlsanity.com/paper/2504.17636/) (2025)
- [LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment](https://mlsanity.com/paper/2503.18640/) (2025)
- [LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images](https://mlsanity.com/paper/2410.11505/) (2024)
- [GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations](https://mlsanity.com/paper/2508.18242/) (2025)
- [SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting](https://mlsanity.com/paper/2503.05174/) (2025)
- [Hierarchical Scoring with 3D Gaussian Splatting for Instance Image-Goal Navigation](https://mlsanity.com/paper/2506.07338/) (2025)
- [SCIGS: 3D Gaussians Splatting from a Snapshot Compressive Image](https://mlsanity.com/paper/2411.12471/) (2024)
- [FalconWing: An Ultra-Light Indoor Fixed-Wing UAV Platform for Vision-Based Autonomy](https://mlsanity.com/paper/2505.01383/) (2025)
- [TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration](https://mlsanity.com/paper/2410.00360/) (2024)
- [GSFeatLoc: Visual Localization Using Feature Correspondence on 3D Gaussian Splatting](https://mlsanity.com/paper/2504.20379/) (2025)
- [SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation](https://mlsanity.com/paper/2507.12027/) (2025)
- [GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation](https://mlsanity.com/paper/2510.16777/) (2025)
- [Asset-Driven Sematic Reconstruction of Dynamic Scene with Multi-Human-Object Interactions](https://mlsanity.com/paper/2512.00547/) (2025)
- [Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancements](https://mlsanity.com/paper/2603.03879/) (2026)
- [L3:Scene-agnostic Visual Localization in the Wild](https://mlsanity.com/paper/2603.07937/) (2026)
- [LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarios](https://mlsanity.com/paper/2604.05402/) (2026)
- [Privacy-Preserving Structureless Visual Localization via Image Obfuscation](https://mlsanity.com/paper/2604.12068/) (2026)
- [Pose Anything Anywhere:Model-free Object Poses from Arbitrary References](https://mlsanity.com/paper/2606.23634/) (2026)
- [Accuracy potential of visual localization exploiting high-end street-level imagery](https://mlsanity.com/paper/2607.24409/) (2026)
- [LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation](https://mlsanity.com/paper/2609.35046/) (2026)

## Abstract (arXiv)

We propose 6DGS to estimate the camera pose of a target RGB image given a 3D Gaussian Splatting (3DGS) model representing the scene. 6DGS avoids the iterative process typical of analysis-by-synthesis methods (e.g. iNeRF) that also require an initialization of the camera pose in order to converge. Instead, our method estimates a 6DoF pose by inverting the 3DGS rendering process. Starting from the object surface, we define a radiant Ellicell that uniformly generates rays departing from each ellipsoid that parameterize the 3DGS model. Each Ellicell ray is associated with the rendering parameters of each ellipsoid, which in turn is used to obtain the best bindings between the target image pixels and the cast rays. These pixel-ray bindings are then ranked to select the best scoring bundle of rays, which their intersection provides the camera center and, in turn, the camera rotation. The proposed solution obviates the necessity of an "a priori" pose for initialization, and it solves 6DoF pose estimation in closed form, without the need for iterations. Moreover, compared to the existing Novel View Synthesis (NVS) baselines for pose estimation, 6DGS can improve the overall average rotational accuracy by 12% and translation accuracy by 22% on real scenes, despite not requiring any initialization pose. At the same time, our method operates near real-time, reaching 15fps on consumer hardware.