mlsanityData to 14 Oct 2026

ReLaGS: Relational Language Gaussian Splatting

arXiv 2603.17605 ↗First posted 18 Mar 2026cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Achieving unified 3D perception and reasoning across tasks such as segmentation, retrieval, and relation understanding remains challenging, as existing methods are either object-centric or rely on costly training for inter-object reasoning. We present a novel framework that constructs a hierarchical language-distilled Gaussian scene and its 3D semantic scene graph without scene-specific training. A Gaussian pruning mechanism refines scene geometry, while a robust multi-view language alignment strategy aggregates noisy 2D features into accurate 3D object embeddings. On top of this hierarchy, we build an open-vocabulary 3D scene graph with Vision Language derived annotations and Graph Neural Network-based relational reasoning. Our approach enables efficient and scalable open-vocabulary 3D reasoning by jointly modeling hierarchical semantics and inter/intra-object relationships, validated across tasks including open-vocabulary segmentation, scene graph generation, and relation-guided retrieval. Project page: https://dfki-av.github.io/ReLaGS/

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 45 of its 51 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

45 of 51 references.

References · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Segment Anythingcited by 8,234
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  7. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  8. 2023LERF: Language Embedded Radiance Fieldscited by 543
  9. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 473
  10. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  11. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 365
  12. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
33 more
  1. 2016Visual Relationship Detection with Language Priorscited by 334
  2. 2018Graph R-CNN for Scene Graph Generationcited by 298
  3. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 281
  4. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 208
  5. 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 208
  6. 2019RIO: 3D Object Instance Re-Localization in Changing Indoor Environmentscited by 188
  7. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 163
  8. 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 145
  9. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  10. 2023Weakly Supervised 3D Open-vocabulary Segmentationcited by 135
  11. 2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 80
  12. 2024OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Viewscited by 69
  13. 2024Splat-Nav: Safe Real-Time Robot Navigation in Gaussian Splatting Mapscited by 55
  14. 2024GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplanecited by 53
  15. 2025Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registrationcited by 51
  16. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  17. 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 43
  18. 2025LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPScited by 41
  19. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  20. 2024LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenescited by 37
  21. 2024SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussianscited by 33
  22. 2023SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generationcited by 27
  23. 2025SplatTalk: 3D VQA with Gaussian Splattingcited by 24
  24. 2024RelationField: Relate Anything in Radiance Fieldscited by 16
  25. 2025Tackling View-Dependent Semantics in 3D Language Gaussian Splattingcited by 16
  26. 2025Universal Scene Graph Generationcited by 11
  27. 2025VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understandingcited by 11
  28. 2025CF3: Compact and Fast 3D Feature Fieldscited by 11
  29. 2025Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphscited by 10
  30. 2025Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splattingcited by 9
  31. 2025GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understandingcited by 8
  32. 2025Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360deg Scenescited by 8
  33. 2025Splat Feature Solvercited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Relation-Centric Open-Vocabulary 3D Gaussian Segmentationcited by 1
  2. 2026NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splattingcited by 0
  3. 2026CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understandingcited by 0
  4. 2026GraphWrit3R: End-to-End 3D Scene Graph Writingcited by 0
  5. 2026EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentationcited by 0
  6. 2026DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussianscited by 0