mlsanityData to 7 Oct 2026

EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

arXiv 2209.14941 ↗First posted 29 Sep 2022cs.CV cs.ROcited by 98

Not on the map. Why?

Abstract (arXiv)

3D visual grounding aims to find the object within point clouds mentioned by free-form natural language descriptions with rich semantic cues. However, existing methods either extract the sentence-level features coupling all words or focus more on object names, which would lose the word-level information or neglect other attributes. To alleviate these issues, we present EDA that Explicitly Decouples the textual attributes in a sentence and conducts Dense Alignment between such fine-grained language and point cloud objects. Specifically, we first propose a text decoupling module to produce textual features for every semantic component. Then, we design two losses to supervise the dense matching between two modalities: position alignment loss and semantic alignment loss. On top of that, we further introduce a new visual grounding task, locating objects without object names, which can thoroughly evaluate the model's dense alignment capacity. Through experiments, we achieve state-of-the-art performance on two widely-adopted 3D visual grounding datasets, ScanRefer and SR3D/NR3D, and obtain absolute leadership on our newly-proposed task. The source code is available at https://github.com/yanmin-wu/EDA.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). Builds on 47 of its 80 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

47 of 80 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  11. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  12. 2021Grounded Language-Image Pre-trainingcited by 1,147
35 more
  1. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  2. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  3. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  4. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 446
  5. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 340
  6. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 330
  7. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  8. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 300
  9. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  10. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
  11. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  12. 2020Scan2Cap: Context-aware Dense Captioning in RGB-D Scanscited by 215
  13. 2021Group-Free 3D Object Detection via Transformerscited by 215
  14. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  15. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  16. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  17. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128
  18. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  19. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  20. 20223D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selectioncited by 109
  21. 2022CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attentioncited by 103
  22. 2022Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Modelscited by 95
  23. 2021LanguageRefer: Spatial-Language Model for 3D Visual Groundingcited by 88
  24. 2021TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Groundingcited by 86
  25. 2021Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloudcited by 81
  26. 2022X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioningcited by 70
  27. 2022HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigationcited by 69
  28. 2022Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoningcited by 69
  29. 2022Can Language Understand Depth?cited by 66
  30. 2019Learning Cross-modal Context Graph for Visual Groundingcited by 49
  31. 2022MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenescited by 46
  32. 2022Spatiality-guided Transformer for 3D Dense Captioning on Point Cloudscited by 40
  33. 2021Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Imagescited by 33
  34. 2021Knowledge-based Embodied Question Answeringcited by 29
  35. 2019Embodied Language Grounding with 3D Visual Feature Representationscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 16; 2024: 28; 2025: 37; 2026: 16.

98 papers.

Sort:

By area:

  1. 2023LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planningcited by 206
  2. 2023Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Followingcited by 192
  3. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  4. 2023Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifierscited by 170
  5. 2023LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmarkcited by 169
  6. 2023Multi3DRefer: Grounding Text Description to Multiple 3D Objectscited by 142
  7. 2024SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understandingcited by 130
  8. 2025GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Modelscited by 106
  9. 2024Unifying 3D Vision-Language Understanding via Promptable Queriescited by 70
  10. 2024SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Groundingcited by 66
  11. 2023Visual Programming for Zero-shot Open-Vocabulary 3D Visual Groundingcited by 64
  12. 2025Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awarenesscited by 61
38 more
  1. 2025Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuningcited by 50
  2. 2023Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioningcited by 38
  3. 20233D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentationcited by 36
  4. 2024InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perceptioncited by 35
  5. 2024SegPoint: Segment Any Point Cloud via Large Language Modelcited by 34
  6. 2022ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenescited by 32
  7. 2023Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Groundingcited by 32
  8. 2023M3DBench: Let's Instruct Large Models with Multi-modal 3D Promptscited by 32
  9. 2024Robin3D: Improving 3D Large Language Model via Robust Instruction Tuningcited by 26
  10. 2024RefMask3D: Language-Guided Transformer for 3D Referring Segmentationcited by 25
  11. 2024A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directionscited by 24
  12. 2025Multimodal Referring Segmentation: A Surveycited by 22
  13. 2024Multi-branch Collaborative Learning Network for 3D Visual Groundingcited by 20
  14. 20243D-GRES: Generalized 3D Referring Expression Segmentationcited by 18
  15. 2024Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehensioncited by 17
  16. 2025TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Groundingcited by 17
  17. 2024Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intentioncited by 16
  18. 2025MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentationcited by 16
  19. 2023CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Datacited by 15
  20. 2023Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluationcited by 12
  21. 2025NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Drivingcited by 12
  22. 2025DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Groundingcited by 12
  23. 2025SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Groundingcited by 12
  24. 2024RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentationcited by 11
  25. 2025SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenescited by 11
  26. 2023Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scanscited by 10
  27. 2025AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referringcited by 10
  28. 2024Task-oriented Sequential Grounding and Navigation in 3D Scenescited by 9
  29. 2023WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Languagecited by 8
  30. 2025CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Frameworkcited by 8
  31. 2025ViewSRD: 3D Visual Grounding via Structured Multi-View Decompositioncited by 8
  32. 20253EED: Ground Everything Everywhere in 3Dcited by 8
  33. 2024Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problemscited by 7
  34. 2025ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Groundingcited by 7
  35. 2025Language-to-Space Programming for Training-Free 3D Visual Groundingcited by 7
  36. 2023A Unified Framework for 3D Point Cloud Visual Groundingcited by 6
  37. 2025OpenBox: Annotate Any Bounding Boxes in 3Dcited by 6
  38. 2024Unified Scene Representation and Reconstruction for 3D Large Language Modelscited by 5

50 most cited of 98 All 98 (JSON)