# Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration

arXiv: https://arxiv.org/abs/2606.29782 · HTML: https://mlsanity.com/paper/2606.29782/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [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)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization](https://mlsanity.com/paper/2201.13360/) (2022)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [Reducing the Memory Footprint of 3D Gaussian Splatting](https://mlsanity.com/paper/2406.17074/) (2024)
- [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://mlsanity.com/paper/2103.04256/) (2021)
- [3D Registration with Maximal Cliques](https://mlsanity.com/paper/2305.10854/) (2023)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [LoopSplat: Loop Closure by Registering 3D Gaussian Splats](https://mlsanity.com/paper/2408.10154/) (2024)
- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph](https://mlsanity.com/paper/2406.07113/) (2024)
- [SGAligner : 3D Scene Alignment with Scene Graphs](https://mlsanity.com/paper/2304.14880/) (2023)
- [GaussReg: Fast 3D Registration with Gaussian Splatting](https://mlsanity.com/paper/2407.05254/) (2024)
- [SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks](https://mlsanity.com/paper/2403.19474/) (2024)
- [Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation](https://mlsanity.com/paper/1801.08361/) (2018)
- [Pyramid Semantic Graph-based Global Point Cloud Registration with Low Overlap](https://mlsanity.com/paper/2307.12116/) (2023)
- [NeRFuser: Large-Scale Scene Representation by NeRF Fusion](https://mlsanity.com/paper/2305.13307/) (2023)
- [PhotoReg: Photometrically Registering 3D Gaussian Splatting Models](https://mlsanity.com/paper/2410.05044/) (2024)

## Abstract (arXiv)

Merging multiple 3D Gaussian Splatting (3DGS) scenes into a single unified Gaussian representation is essential for large-scale 3D mapping and long-term map management. Despite its importance, this area remains underexplored, and existing solutions exhibit several limitations. Learning-based methods attempt direct correspondence between Gaussian primitives and require training on large 3DGS datasets. Image-based optimization methods depend heavily on coarse initialization from generic foundation models and often incur expensive refinement. We present ourmodel. Our method constructs a 3D scene graph from a 3DGS and its rendered images, textitreformulating 3DGS registration as a graph registration problem. The proposed 3D scene graph represents each 3DGS at a higher-level representation, enabling a globally consistent understanding of semantic information and structural context for accurate registration. To further construct a seamless unified scene, we introduce a Self-Supervised Test-Time Optimization. Naively merging two 3D Gaussian scenes often suffers from occlusion artifacts such as hollows and floaters. To alleviate this issue, we refine the merged Gaussians to preserve visual consistency between the original scenes and the merged scene. We evaluate our method on real and synthetic benchmarks, demonstrating competitive registration accuracy and merged scene rendering quality.