mlsanityData to 14 Oct 2026

ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition

arXiv 2507.11261 ↗First posted 15 Jul 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsistencies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a framework that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Relation Decoupling (SRD) module restructures complex multi-anchor queries into a set of targeted single-anchor statements, generating a structured set of perspective-aware descriptions that clarify positional relationships. These decomposed representations serve as the foundation for the Multi-view Textual-Scene Interaction (Multi-TSI) module, which integrates textual and scene features across multiple viewpoints using shared, Cross-modal Consistent View Tokens (CCVTs) to preserve spatial correlations. Finally, a Textual-Scene Reasoning module synthesizes multi-view predictions into a unified and robust 3D visual grounding. Experiments on 3D visual grounding datasets show that ViewSRD significantly outperforms state-of-the-art methods, particularly in complex queries requiring precise spatial differentiation. Code is available at https://github.com/visualjason/ViewSRD.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 40 of its 60 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

40 of 60 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 452
  7. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 415
  8. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  9. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  10. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 252
  11. 2023Multi3DRefer: Grounding Text Description to Multiple 3D Objectscited by 146
  12. 2022Multi-View Transformer for 3D Visual Groundingcited by 140
28 more
  1. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128
  2. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  3. 2023Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehiclescited by 100
  4. 2022EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Groundingcited by 99
  5. 2021LanguageRefer: Spatial-Language Model for 3D Visual Groundingcited by 89
  6. 2023Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Drivingcited by 89
  7. 2021TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Groundingcited by 86
  8. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  9. 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
  10. 2024Unifying 3D Vision-Language Understanding via Promptable Queriescited by 70
  11. 2023Visual Programming for Zero-shot Open-Vocabulary 3D Visual Groundingcited by 64
  12. 2024Multi-modal Situated Reasoning in 3D Scenescited by 51
  13. 2023SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesiscited by 41
  14. 2024MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotationscited by 40
  15. 2023Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representationscited by 37
  16. 2023Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open Worldcited by 35
  17. 2024Situational Awareness Matters in 3D Vision Language Reasoningcited by 33
  18. 2024MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Groundingcited by 29
  19. 2022Iterative Scene Graph Generation with Generative Transformerscited by 22
  20. 2024G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priorscited by 20
  21. 2023CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Groundingcited by 13
  22. 2025RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillationcited by 9
  23. 2024Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistencycited by 6
  24. 2025SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generationcited by 6
  25. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  26. 2024VrdONE: One-stage Video Visual Relation Detectioncited by 4
  27. 2025SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimationcited by 2
  28. 2022Visual Question Answering From Another Perspective: CLEVR Mental Rotation Testscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2026LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generationcited by 6
  2. 2025PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Groundingcited by 3
  3. 2026UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsingcited by 1
  4. 2025OpenGround: Planning-based Online Perception for Open-World 3D Visual Groundingcited by 0
  5. 2026PruneGround: Plug-and-play Spatial Pruning for 3D Visual Groundingcited by 0
  6. 2026Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Groundingcited by 0
  7. 2026CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Groundingcited by 0
  8. 2026DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussianscited by 0