mlsanityData to 14 Oct 2026

3D-DRES: Detailed 3D Referring Expression Segmentation

arXiv 2603.02896 ↗First posted 3 Mar 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natural language expressions. To address this challenge, we introduce Detailed 3D Referring Expression Segmentation (3D-DRES), a new task that provides a phrase to 3D instance mapping, aiming at enhancing fine-grained 3D vision language understanding. To support 3D-DRES, we present DetailRefer, a new dataset comprising 54,432 descriptions spanning 11,054 distinct objects. Unlike previous datasets, DetailRefer implements a pioneering phrase-instance annotation paradigm where each referenced noun phrase is explicitly mapped to its corresponding 3D elements. Additionally, we introduce DetailBase, a purposefully streamlined yet effective baseline architecture that supports dual-mode segmentation at both sentence and phrase levels. Our experimental results demonstrate that models trained on DetailRefer not only excel at phrase-level segmentation but also show surprising improvements on traditional 3D-RES benchmarks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

42 of 59 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  4. 2015VQA: Visual Question Answeringcited by 2,506
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  6. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  7. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  8. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
  9. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  10. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  11. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  12. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 452
30 more
  1. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  2. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 346
  3. 2016Segmentation from Natural Language Expressionscited by 257
  4. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 141
  5. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128
  6. 2021SAT: 2D Semantics Assisted Training for 3D Visual Groundingcited by 124
  7. 2022Language Conditioned Spatial Relation Reasoning for 3D Object Groundingcited by 122
  8. 20223D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selectioncited by 110
  9. 2022EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Groundingcited by 99
  10. 2021Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloudcited by 81
  11. 2022X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioningcited by 70
  12. 2024Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Trainingcited by 64
  13. 2024ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilitiescited by 47
  14. 20233D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentationcited by 36
  15. 2021Panoptic Narrative Groundingcited by 27
  16. 2025IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasiscited by 26
  17. 20233DRP-Net: 3D Relative Position-aware Network for 3D Visual Groundingcited by 25
  18. 2024RefMask3D: Language-Guided Transformer for 3D Referring Segmentationcited by 25
  19. 2023GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detectioncited by 20
  20. 2024Multi-branch Collaborative Learning Network for 3D Visual Groundingcited by 20
  21. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  22. 20243D-GRES: Generalized 3D Referring Expression Segmentationcited by 18
  23. 2024SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentationcited by 17
  24. 2025TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Groundingcited by 17
  25. 2023Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Networkcited by 13
  26. 2022PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Groundingcited by 12
  27. 2025IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentationcited by 8
  28. 2023Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Groundingcited by 6
  29. 2025ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Groundingcited by 5
  30. 2024Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Groundingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generationcited by 6