mlsanityData to 7 Oct 2026

SGAligner : 3D Scene Alignment with Scene Graphs

arXiv 2304.14880 ↗First posted 28 Apr 2023cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Building 3D scene graphs has recently emerged as a topic in scene representation for several embodied AI applications to represent the world in a structured and rich manner. With their increased use in solving downstream tasks (eg, navigation and room rearrangement), can we leverage and recycle them for creating 3D maps of environments, a pivotal step in agent operation? We focus on the fundamental problem of aligning pairs of 3D scene graphs whose overlap can range from zero to partial and can contain arbitrary changes. We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios (ie, unknown overlap -- if any -- and changes in the environment). We get inspired by multi-modality knowledge graphs and use contrastive learning to learn a joint, multi-modal embedding space. We evaluate on the 3RScan dataset and further showcase that our method can be used for estimating the transformation between pairs of 3D scenes. Since benchmarks for these tasks are missing, we create them on this dataset. The code, benchmark, and trained models are available on the project website.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 38 of its 63 references that are in the map. First posted on arXiv 28 Apr 2023.

Builds on

38 of 63 references.

References · 38

  1. 2017Graph Attention Networkscited by 8,854
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2020PCT: Point cloud transformercited by 730
  5. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  6. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  7. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 280
  8. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  9. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
  10. 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 202
  11. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  12. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 187
26 more
  1. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  2. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 175
  3. 2022Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimizationcited by 175
  4. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 160
  5. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  6. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  7. 20203D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humanscited by 141
  8. 2017Graph-Cut RANSACcited by 133
  9. 2019MMKG: Multi-Modal Knowledge Graphscited by 104
  10. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  11. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 83
  12. 2019Multi-view Knowledge Graph Embedding for Entity Alignmentcited by 74
  13. 20193-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agentscited by 74
  14. 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
  15. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 50
  16. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  17. 2020Visual Pivoting for (Unsupervised) Entity Alignmentcited by 46
  18. 2022Continuous Scene Representations for Embodied AIcited by 39
  19. 2022Multi-modal Contrastive Representation Learning for Entity Alignmentcited by 37
  20. 20223D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphscited by 24
  21. 2021Multi-modal Entity Alignment in Hyperbolic Spacecited by 19
  22. 2022Sequential Manipulation Planning on Scene Graphcited by 16
  23. 2019HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubscited by 12
  24. 2018A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigationcited by 9
  25. 2020PointNet on FPGA for Real-Time LiDAR Point Cloud Processingcited by 3
  26. 2020Bridging Scene Understanding and Task Execution with Flexible Simulation Environmentscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 9; 2025: 8; 2026: 10.

30 papers.

Sort:

By area:

  1. 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 76
  2. 2025Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spacescited by 53
  3. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  4. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  5. 2023SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstructioncited by 20
  6. 2023Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph predictioncited by 18
  7. 2024RelationField: Relate Anything in Radiance Fieldscited by 16
  8. 2023Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environmentscited by 15
  9. 2025CrossOver: 3D Scene Cross-Modal Alignmentcited by 12
  10. 2024SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Taskscited by 10
  11. 2024Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Descriptioncited by 9
  12. 2025SG-Reg: Generalizable and Efficient Scene Graph Registrationcited by 8
18 more
  1. 2024OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understandingcited by 4
  2. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  3. 20263D Scene Graphs: Open Challenges and Future Directionscited by 4
  4. 2024Self-Localized Collaborative Perceptioncited by 2
  5. 2024TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understandingcited by 2
  6. 2025SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignmentcited by 2
  7. 2025Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Predictioncited by 2
  8. 2025Object-X: Learning to Reconstruct Multi-Modal 3D Object Representationscited by 1
  9. 2025Finding 3D Scene Analogies with Multimodal Foundation Modelscited by 1
  10. 2026MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environmentscited by 0
  11. 2026PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matchingcited by 0
  12. 2026OpenSGA: Efficient 3D Scene Graph Alignment in the Open Worldcited by 0
  13. 2026PROSE: Training-Free Egocentric Scene Registration with Vision-Language Modelscited by 0
  14. 2026From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generationcited by 0
  15. 2026Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registrationcited by 0
  16. 2026Computing Monetary Risk Measures in Linear Timecited by 0
  17. 2026Geometric 2D Scene Graph Generationcited by 0
  18. 2026VideoReloc: Long-Term Indoor Video Relocalization against a Kilobyte-Scale Semantic Scene Graphcited by 0