mlsanityData to 14 Oct 2026

SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences

arXiv 2602.02974 ↗First posted 3 Feb 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce SceneLinker, a novel framework that generates compositional 3D scenes via semantic scene graph from RGB sequences. To adaptively experience Mixed Reality (MR) content based on each user's space, it is essential to generate a 3D scene that reflects the real-world layout by compactly capturing the semantic cues of the surroundings. Prior works struggled to fully capture the contextual relationship between objects or mainly focused on synthesizing diverse shapes, making it challenging to generate 3D scenes aligned with object arrangements. We address these challenges by designing a graph network with cross-check feature attention for scene graph prediction and constructing a graph-variational autoencoder (graph-VAE), which consists of a joint shape and layout block for 3D scene generation. Experiments on the 3RScan/3DSSG and SG-FRONT datasets demonstrate that our approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations, even in complex indoor environments and under challenging scene graph constraints. Our work enables users to generate consistent 3D spaces from their physical environments via scene graphs, allowing them to create spatial MR content. Project page is https://scenelinker2026.github.io.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 56 of its 67 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

56 of 67 references.

References · 56

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Segment Anythingcited by 8,234
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  8. 2017Neural Discrete Representation Learningcited by 4,712
  9. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  11. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  12. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
38 more
  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  2. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  3. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  4. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  5. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  6. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  7. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  8. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  9. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 365
  10. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
  11. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  12. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 294
  13. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 281
  14. 2025SAM 3D: 3Dfy Anything in Imagescited by 247
  15. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  16. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 208
  17. 2024Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigationcited by 196
  18. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 188
  19. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 184
  20. 2022Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimizationcited by 178
  21. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 163
  22. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 117
  23. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 117
  24. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 97
  25. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 96
  26. 2024I-Design: Personalized LLM Interior Designercited by 87
  27. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 84
  28. 20193-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agentscited by 74
  29. 2024EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusioncited by 67
  30. 2020End-to-End Optimization of Scene Layoutcited by 52
  31. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 49
  32. 2024REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignmentcited by 45
  33. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  34. 2024Khronos: A Unified Approach for Spatio-Temporal Metric-Semantic SLAM in Dynamic Environmentscited by 36
  35. 2018Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoningcited by 27
  36. 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
  37. 2020Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graphcited by 19
  38. 2025MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generationcited by 19

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priorscited by 1
  2. 2026SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenescited by 0
  3. 2026SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RLcited by 0