mlsanityData to 7 Oct 2026

Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention

arXiv 2410.22306 ↗First posted 29 Oct 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Multi-object 3D Grounding involves locating 3D boxes based on a given query phrase from a point cloud. It is a challenging and significant task with numerous applications in visual understanding, human-computer interaction, and robotics. To tackle this challenge, we introduce D-LISA, a two-stage approach incorporating three innovations. First, a dynamic vision module that enables a variable and learnable number of box proposals. Second, a dynamic camera positioning that extracts features for each proposal. Third, a language-informed spatial attention module that better reasons over the proposals to output the final prediction. Empirically, experiments show that our method outperforms the state-of-the-art methods on multi-object 3D grounding by 12.8% (absolute) and is competitive in single-object 3D grounding.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 57 references that are in the map. First posted on arXiv 29 Oct 2024.

Builds on

45 of 57 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  4. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  5. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 446
  6. 2018MAttNet: Modular Attention Network for Referring Expression Comprehensioncited by 427
  7. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  8. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  9. 20233D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignmentcited by 201
  10. 2019A Fast and Accurate One-Stage Approach to Visual Groundingcited by 194
  11. 2021Multimodal Virtual Point 3D Detectioncited by 166
  12. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
33 more
  1. 2021Referring Transformer: A One-step Approach to Multi-task Visual Groundingcited by 143
  2. 2023Multi3DRefer: Grounding Text Description to Multiple 3D Objectscited by 142
  3. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  4. 2018Learning to Assemble Neural Module Tree Networks for Visual Groundingcited by 139
  5. 2022Multi-View Transformer for 3D Visual Groundingcited by 138
  6. 2020Improving One-stage Visual Grounding by Recursive Sub-query Constructioncited by 137
  7. 2023LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agentcited by 134
  8. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128
  9. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  10. 2022Language Conditioned Spatial Relation Reasoning for 3D Object Groundingcited by 121
  11. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  12. 2019A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehensioncited by 111
  13. 2019Dynamic Graph Attention for Referring Expression Comprehensioncited by 111
  14. 20223D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selectioncited by 109
  15. 2018Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networkscited by 102
  16. 2021LanguageRefer: Spatial-Language Model for 3D Visual Groundingcited by 88
  17. 2021TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Groundingcited by 86
  18. 2021Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloudcited by 81
  19. 2019Zero-Shot Grounding of Objects from Natural Language Queriescited by 79
  20. 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
  21. 2022UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Groundingcited by 69
  22. 2023Visual Programming for Zero-shot Open-Vocabulary 3D Visual Groundingcited by 64
  23. 2020Graph-Structured Referring Expression Reasoning in The Wildcited by 58
  24. 2023NS3D: Neuro-Symbolic Grounding of 3D Objects and Relationscited by 57
  25. 2017Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queriescited by 56
  26. 2021D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Groundingcited by 52
  27. 2022TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformercited by 41
  28. 2022Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Groundingcited by 41
  29. 2022ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenescited by 32
  30. 2023Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Groundingcited by 32
  31. 2024MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Groundingcited by 29
  32. 20233DRP-Net: 3D Relative Position-aware Network for 3D Visual Groundingcited by 25
  33. 2023CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Groundingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMscited by 7
  2. 20253DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignmentcited by 0
  3. 2025Auto-Vocabulary 3D Object Detectioncited by 0
  4. 2026PruneGround: Plug-and-play Spatial Pruning for 3D Visual Groundingcited by 0