# SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks arXiv: https://arxiv.org/abs/2403.19474 ยท HTML: https://mlsanity.com/paper/2403.19474/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 40 of its 57 references that are in the map. - First posted on arXiv 28 Mar 2024. ## Builds on (most cited first, 30 of 40) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016) - [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016) - [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018) - [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019) - [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019) - [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021) - [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016) - [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020) - [3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera](https://mlsanity.com/paper/1910.02527/) (2019) - [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019) - [Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions](https://mlsanity.com/paper/2004.03967/) (2020) - [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022) - [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019) - [Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization](https://mlsanity.com/paper/2201.13360/) (2022) - [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018) - [SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences](https://mlsanity.com/paper/2103.14898/) (2021) - [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021) - [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021) - [Graph-Cut RANSAC](https://mlsanity.com/paper/1706.00984/) (2017) - [SOON: Scenario Oriented Object Navigation with Graph-based Exploration](https://mlsanity.com/paper/2103.17138/) (2021) - [Learning Combinatorial Embedding Networks for Deep Graph Matching](https://mlsanity.com/paper/1904.00597/) (2019) - [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://mlsanity.com/paper/2103.04256/) (2021) - [SimGNN: A Neural Network Approach to Fast Graph Similarity Computation](https://mlsanity.com/paper/1808.05689/) (2018) - [Deep Graph Matching Consensus](https://mlsanity.com/paper/2001.09621/) (2020) - [Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs](https://mlsanity.com/paper/2108.08841/) (2021) - [Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud](https://mlsanity.com/paper/2103.16381/) (2021) - [Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth](https://mlsanity.com/paper/2105.04550/) (2021) - [OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration](https://mlsanity.com/paper/2103.00937/) (2021) - [Neural Subgraph Matching](https://mlsanity.com/paper/2007.03092/) (2020) ## Built on by (most cited first, 10 of 10) - [CrossOver: 3D Scene Cross-Modal Alignment](https://mlsanity.com/paper/2502.15011/) (2025) - [SG-Reg: Generalizable and Efficient Scene Graph Registration](https://mlsanity.com/paper/2504.14440/) (2025) - [Learning 3D Scene Analogies with Neural Contextual Scene Maps](https://mlsanity.com/paper/2503.15897/) (2025) - [TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding](https://mlsanity.com/paper/2411.10509/) (2024) - [SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment](https://mlsanity.com/paper/2509.20401/) (2025) - [MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments](https://mlsanity.com/paper/2602.04152/) (2026) - [OpenSGA: Efficient 3D Scene Graph Alignment in the Open World](https://mlsanity.com/paper/2605.10484/) (2026) - [PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models](https://mlsanity.com/paper/2606.16569/) (2026) - [From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generation](https://mlsanity.com/paper/2606.27412/) (2026) - [Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration](https://mlsanity.com/paper/2606.29782/) (2026) ## Abstract (arXiv) Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many downstream tasks such as scene graph aided point cloud registration, mosaicking, overlap checking, and robot navigation. In this work, we treat 3D scene graph alignment as a partial graph-matching problem and propose to solve it with a graph neural network. We reuse the geometric features learned by a point cloud registration method and associate the clustered point-level geometric features with the node-level semantic feature via our designed feature fusion module. Partial matching is enabled by using a learnable method to select the top-k similar node pairs. Subsequent downstream tasks such as point cloud registration are achieved by running a pre-trained registration network within the matched regions. We further propose a point-matching rescoring method, that uses the node-wise alignment of the 3D scene graph to reweight the matching candidates from a pre-trained point cloud registration method. It reduces the false point correspondences estimated especially in low-overlapping cases. Experiments show that our method improves the alignment accuracy by 10~20% in low-overlap and random transformation scenarios and outperforms the existing work in multiple downstream tasks.