mlsanityData to 7 Oct 2026

3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs

arXiv 2209.07896 ↗First posted 16 Sep 2022cs.RO cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Numerous applications require robots to operate in environments shared with other agents, such as humans or other robots. However, such shared scenes are typically subject to different kinds of long-term semantic scene changes. The ability to model and predict such changes is thus crucial for robot autonomy. In this work, we formalize the task of semantic scene variability estimation and identify three main varieties of semantic scene change: changes in the position of an object, its semantic state, or the composition of a scene as a whole. To represent this variability, we propose the Variable Scene Graph (VSG), which augments existing 3D Scene Graph (SG) representations with the variability attribute, representing the likelihood of discrete long-term change events. We present a novel method, DeltaVSG, to estimate the variability of VSGs in a supervised fashion. We evaluate our method on the 3RScan long-term dataset, showing notable improvements in this novel task over existing approaches. Our method DeltaVSG achieves an accuracy of 77.1% and a recall of 72.3%, often mimicking human intuition about how indoor scenes change over time. We further show the utility of VSG prediction in the task of active robotic change detection, speeding up task completion by 66.0% compared to a scene-change-unaware planner. We make our code available as open-source.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

34 of 56 references.

References · 34

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  3. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  4. 2016Visual Relationship Detection with Language Priorscited by 333
  5. 2018Fully Convolutional Siamese Networks for Change Detectioncited by 305
  6. 2018Graph R-CNN for Scene Graph Generationcited by 296
  7. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 280
  8. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
  9. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 187
  10. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 181
  11. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  12. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 165
22 more
  1. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  2. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  3. 20203D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humanscited by 141
  4. 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
  5. 2018Visual Semantic Navigation using Scene Priorscited by 127
  6. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
  7. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  8. 2018Fusion++: Volumetric Object-Level SLAMcited by 97
  9. 2020Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphscited by 83
  10. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 83
  11. 2019Volumetric Instance-Aware Semantic Mapping and 3D Object Discoverycited by 79
  12. 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
  13. 2013Indoor Semantic Segmentation using depth informationcited by 56
  14. 2020End-to-End Optimization of Scene Layoutcited by 52
  15. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 50
  16. 2021Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistencycited by 38
  17. 2021ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environmentscited by 28
  18. 2020Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graphcited by 19
  19. 2020Semantic and Geometric Modeling with Neural Message Passing in 3D Scene Graphs for Hierarchical Mechanical Searchcited by 14
  20. 2020Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusioncited by 13
  21. 2022Spatial Commonsense Graph for Object Localisation in Partial Scenescited by 9
  22. 2020Semantic Change Pattern Analysiscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 8; 2026: 7.

24 papers.

Sort:

By area:

  1. 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 76
  2. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  3. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  4. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  5. 2025Describe Anything Anywhere At Any Momentcited by 19
  6. 2023Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph predictioncited by 18
  7. 2024RelationField: Relate Anything in Radiance Fieldscited by 16
  8. 2024Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphscited by 10
  9. 2025Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamicscited by 5
  10. 2024Belief Scene Graphs: Expanding Partial Scenes with Objects through Computation of Expectationcited by 4
  11. 2025SceneDiff: A Benchmark and Method for Multiview Object Change Detectioncited by 4
  12. 20263D Scene Graphs: Open Challenges and Future Directionscited by 4
12 more
  1. 2025Estimating Commonsense Scene Composition on Belief Scene Graphscited by 3
  2. 2024BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understandingcited by 2
  3. 2025Perpetua: Multi-Hypothesis Persistence Modeling for Semi-Static Environmentscited by 2
  4. 2025Integrating Prior Observations for Incremental 3D Scene Graph Predictioncited by 2
  5. 2026From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splattingcited by 2
  6. 2025M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environmentscited by 1
  7. 2025ChangingGrounding: 3D Visual Grounding in Changing Scenescited by 1
  8. 2026VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoningcited by 1
  9. 2026MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environmentscited by 0
  10. 2026TERDNet: Transformer Encoder-Recurrent Decoder Network for Scene Change Detectioncited by 0
  11. 2026Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environmentscited by 0
  12. 2026Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphscited by 0