mlsanityData to 7 Oct 2026

Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions

arXiv 2004.03967 ↗First posted 8 Apr 2020cs.CVcited by 205

Not on the map. Why?

Abstract (arXiv)

Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic segmentation and scene layout prediction. In our work we focus on scene graphs, a data structure that organizes the entities of a scene in a graph, where objects are nodes and their relationships modeled as edges. We leverage inference on scene graphs as a way to carry out 3D scene understanding, mapping objects and their relationships. In particular, we propose a learned method that regresses a scene graph from the point cloud of a scene. Our novel architecture is based on PointNet and Graph Convolutional Networks (GCN). In addition, we introduce 3DSSG, a semi-automatically generated dataset, that contains semantically rich scene graphs of 3D scenes. We show the application of our method in a domain-agnostic retrieval task, where graphs serve as an intermediate representation for 3D-3D and 2D-3D matching.

Key facts. Cited by 205 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 22; 2023: 24; 2024: 44; 2025: 44; 2026: 54.

205 papers.

Sort:

By area:

  1. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  2. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  3. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 357
  4. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 297
  5. 2024Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigationcited by 195
  6. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  7. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  8. 2024SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understandingcited by 130
  9. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  10. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  11. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  12. 2022CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoningcited by 119
38 more
  1. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 83
  2. 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 76
  3. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  4. 20243D-Mem: 3D Scene Memory for Embodied Exploration and Reasoningcited by 73
  5. 2024Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphscited by 72
  6. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  7. 2024ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigationcited by 67
  8. 2024EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusioncited by 66
  9. 2021Learning to Generate Scene Graph from Natural Language Supervisioncited by 64
  10. 2024Volumetric Environment Representation for Vision-Language Navigationcited by 63
  11. 2023NS3D: Neuro-Symbolic Grounding of 3D Objects and Relationscited by 57
  12. 2025UniGoal: Towards Universal Zero-shot Goal-oriented Navigationcited by 56
  13. 2023CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusioncited by 54
  14. 2023SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environmentscited by 53
  15. 2025Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spacescited by 53
  16. 20224D-OR: Semantic Scene Graphs for OR Domain Modelingcited by 49
  17. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  18. 2022MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenescited by 46
  19. 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulationcited by 46
  20. 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 42
  21. 2022Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Groundingcited by 41
  22. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  23. 2022Spatiality-guided Transformer for 3D Dense Captioning on Point Cloudscited by 40
  24. 2022Continuous Scene Representations for Embodied AIcited by 39
  25. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  26. 2024GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answeringcited by 37
  27. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  28. 2023Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphscited by 33
  29. 2024DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Modelscited by 33
  30. 2024Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graphcited by 32
  31. 2024Search3D: Hierarchical Open-Vocabulary 3D Segmentationcited by 31
  32. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  33. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  34. 2025Global-Local Tree Search in VLMs for 3D Indoor Scene Generationcited by 29
  35. 2022RU-Net: Regularized Unrolling Network for Scene Graph Generationcited by 28
  36. 2022S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representationscited by 28
  37. 2021Generalized Contrastive Optimization of Siamese Networks for Place Recognitioncited by 27
  38. 2023SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generationcited by 27

50 most cited of 205 All 205 (JSON)