mlsanityData to 7 Oct 2026

Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis

arXiv 2103.05558 ↗First posted 9 Mar 2021cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Scene understanding is a critical problem in computer vision. In this paper, we propose a 3D point-based scene graph generation (mathbfSGGpoint) framework to effectively bridge perception and reasoning to achieve scene understanding via three sequential stages, namely scene graph construction, reasoning, and inference. Within the reasoning stage, an EDGE-oriented Graph Convolutional Network (textttEdgeGCN) is created to exploit multi-dimensional edge features for explicit relationship modeling, together with the exploration of two associated twinning interaction mechanisms between nodes and edges for the independent evolution of scene graph representations. Overall, our integrated mathbfSGGpoint framework is established to seek and infer scene structures of interest from both real-world and synthetic 3D point-based scenes. Our experimental results show promising edge-oriented reasoning effects on scene graph generation studies. We also demonstrate our method advantage on several traditional graph representation learning benchmark datasets, including the node-wise classification on citation networks and whole-graph recognition problems for molecular analysis.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 41 of its 57 references that are in the map. First posted on arXiv 9 Mar 2021.

Builds on

41 of 57 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Graph Attention Networkscited by 8,854
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  11. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
29 more
  1. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  2. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  3. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  4. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  5. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  6. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 446
  7. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  8. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  9. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  10. 2016Visual Relationship Detection with Language Priorscited by 333
  11. 2018Image Generation from Scene Graphscited by 324
  12. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  13. 2018Graph R-CNN for Scene Graph Generationcited by 296
  14. 2018Context Encoding for Semantic Segmentationcited by 289
  15. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  16. 2020Scan2Cap: Context-aware Dense Captioning in RGB-D Scanscited by 215
  17. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
  18. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 187
  19. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  20. 2018Graph-Based Global Reasoning Networkscited by 120
  21. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  22. 2018Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generationcited by 78
  23. 2017Pixels to Graphs by Associative Embeddingcited by 58
  24. 2019SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentationcited by 55
  25. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  26. 2018GRAINS: Generative Recursive Autoencoders for INdoor Scenescited by 38
  27. 2019JSNet: Joint Instance and Semantic Segmentation of 3D Point Cloudscited by 27
  28. 2019LatentGNN: Learning Efficient Non-local Relations for Visual Recognitioncited by 25
  29. 2020GINet: Graph Interaction Network for Scene Parsingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 7; 2024: 5; 2025: 12; 2026: 11.

47 papers.

Sort:

  1. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  2. 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 76
  3. 2022Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuningcited by 54
  4. 2025Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spacescited by 53
  5. 2025PyG 2.0: Scalable Learning on Real World Graphscited by 49
  6. 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 42
  7. 2022Spatiality-guided Transformer for 3D Dense Captioning on Point Cloudscited by 40
  8. 2023Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open Worldcited by 35
  9. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  10. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  11. 2022(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answeringcited by 29
  12. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
35 more
  1. 2023SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generationcited by 27
  2. 20213D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysiscited by 23
  3. 2023SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstructioncited by 20
  4. 2023Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph predictioncited by 18
  5. 2021Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulationcited by 17
  6. 2022Explainability in Graph Neural Networks: An Experimental Surveycited by 16
  7. 2025Universal Scene Graph Generationcited by 11
  8. 2025FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Imagescited by 10
  9. 2022White Matter Tracts are Point Clouds: Neuropsychological Score Prediction and Critical Region Localization via Geometric Deep Learningcited by 9
  10. 2022Language-Assisted 3D Feature Learning for Semantic Scene Understandingcited by 6
  11. 2022Rethinking Rotation Invariance with Point Cloud Registrationcited by 5
  12. 2024Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labelingcited by 5
  13. 2025Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Imagescited by 5
  14. 2022Explore Contextual Information for 3D Scene Graph Generationcited by 4
  15. 20223D Shape Knowledge Graph for Cross-domain 3D Shape Retrievalcited by 4
  16. 20263D Scene Graphs: Open Challenges and Future Directionscited by 4
  17. 2026SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequencescited by 3
  18. 2023Instance-incremental Scene Graph Generation from Real-world Point Clouds via Normalizing Flowscited by 2
  19. 2025FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understandingcited by 2
  20. 2025Integrating Prior Observations for Incremental 3D Scene Graph Predictioncited by 2
  21. 2025Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Predictioncited by 2
  22. 2025M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environmentscited by 1
  23. 2025Edge-Centric Relational Reasoning for 3D Scene Graph Predictioncited by 1
  24. 2026VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoningcited by 1
  25. 2026Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spacescited by 1
  26. 2024Advancing Frontiers in SLAM: A Survey of Symbolic Representation and Human-Machine Teaming in Environmental Mappingcited by 0
  27. 2025LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Groundingcited by 0
  28. 2025Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoderscited by 0
  29. 2026MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environmentscited by 0
  30. 2026Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learningcited by 0
  31. 2026SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matchingcited by 0
  32. 2026SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generationcited by 0
  33. 2026From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generationcited by 0
  34. 2026NoPA: Non-Parametric Online 3D Scene Graph Generationcited by 0
  35. 2026GraphWrit3R: End-to-End 3D Scene Graph Writingcited by 0