Overview

Three-dimensional visual grounding studies how to locate and identify the objects or regions described by language or images, often predicting a 3D box, point, or mask. Systems combine language and visual features with point-cloud geometry, scene graphs, or multi-view RGB-D evidence; newer approaches also use vision-language models, Gaussian splatting, and tool-using agents. Benchmarks such as ScanRefer, Nr3D, and SceneFun3D test referring expressions, relational descriptions, and functional regions, while open-vocabulary methods aim to handle unseen objects and scenes. Performance is improving, but reliable grounding remains difficult when viewpoints, ambiguous language, occlusion, or metric spatial constraints matter.

Latest papers

CardsList

149 papers12 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.

  1. DACA: Dual-Anchor Collaborative Agent for Zero-Shot 3D Visual Grounding

    Nov 19, 2026Jiaming Liu, Linghe Kong, Guixu Zhang +13D Visual GroundingTool-Using Agents

  2. Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding

    Nov 18, 2026Zihao Zhang, Aming Wu, Yang Li +13D Visual GroundingCausal Reasoning

  3. MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues

    Nov 8, 2026Shijia Zhao, Xusheng Guo, Qiming Xia +43D Visual Grounding

  4. GVT3D: Gesture-Vision-Text Token Enrichment for 3D Embodied Reference Understanding

    Nov 3, 2026Vimarsh Shah, Dulanga Weerakoon, Ajinkya Deshpande +93D Visual GroundingVLMs for Robotics

  5. Lie Routing Vision Language Models for View-Robust 3D Understanding

    Nov 1, 2026Jingjun Yi, Chen Hu, Qi Bi +73D VLMs3D Scene Understanding

  6. QVR3D: Query-Guided Visual Reasoning for Training-Free 3D Grounding

    Oct 31, 2026Jung-Hao Kao, Jing-En Huang, Jia-Wei Liao +43D Visual Grounding

  7. 3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement

    Oct 27, 2026Yongqi Shan, Lu Zhang, Jiazuo Yu +23D Scene Understanding3D VLMs

  8. ClusterSplat: Semantic Cluster Selection for 3D Visual Grounding in Gaussian Splatting

    Oct 27, 2026Jaesung Lee, Hyeontaek Hwang, Gabriel Manalu +13D Visual Grounding3D Referring Segmentation

  9. RelateGS: Reliable Semantic and Relational Evidence for 3D Scene Understanding with Gaussian Splatting

    Oct 24, 2026Seongjun Choi, Sangyoun Lee3D Scene Understanding3D Visual Grounding

  10. GeoLift: Grounding Video Spatial Reasoning in Explicit 3D Maps

    Oct 24, 2026Xinglin Li, TingTing Long, Jingzhi Zhou +3Multimodal Spatial ReasoningVideo Reasoning

  11. Gaussian Episodic Memory for Long-Term Spatiotemporal Reasoning

    Oct 23, 2026Ling-Chia Chen, Abdelrhman Werby, Kaan Aytekin +1Spatiotemporal ReasoningLong-Term Memory for Embodied Agents

  12. P3^3-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models

    Oct 20, 2026Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey +23D VLMs3D Visual Grounding

  13. Do 3D Large Language Models Really Use 3D Evidence?

    Oct 17, 2026Yifei Zhao, Fanyu Zhao, Han Zhang +63D VLMs3D Visual Question Answering

  14. BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding

    Oct 15, 2026Yijie Su, Yakun Zhu, Yi Bin +53D Affordance Grounding3D Visual Grounding

  15. Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

    Oct 13, 2026Yu Wang, Rui Dai, Wei Chen +53D Visual Grounding

  16. Agreement versus Softmax under Spatial Disambiguation

    Oct 9, 2026Michał Zakrzewski, Mariia Shpir, Taras Rumezhak +1Vision-Language Grounding3D Visual Grounding

  17. Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry

    Oct 9, 2026Michał Zakrzewski, Mariia Shpir, Taras RumezhakVision-Language Retrieval3D VLMs

  18. M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding

    Oct 6, 2026Jinsong Zhang, Kejun Wu, Ming Zhu +3Monocular Depth EstimationTool-Using Agents

  19. OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception

    Oct 6, 2026Binh Long Nguyen, Kien Nguyen, Clinton Fookes +1Language-Embedded 3DGSOpen-Vocabulary 3D Segmentation

  20. ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation

    Oct 5, 2026Tzu-Hsin Hsieh, Ricardo Marroquim3D Scene Editing3D Visual Grounding

  21. Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding

    Oct 5, 2026Junming Huang, Zini Chen, Shuaiying Hou +3Active View Selection3D Visual Question Answering

  22. Scaling 3D Visual Grounding in Abdominal CT

    Oct 2, 2026Sam Church, Danyal Maqbool, Joshua D. Warner +4Medical Image Grounding3D Visual Grounding

  23. Task-Adaptive Grounded 3D-Programmers Using 2D VLMs

    Oct 1, 2026Arman Raayatsanati, Sombit Dey, Anna-Maria Halacheva +33D Scene Generation3D Scene Understanding

  24. RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation

    Oct 1, 2026Minsu Kim, Jaesung Choe, Jiwoo Lee +23D ViTs3D Spatial Reasoning

  25. HiWE: Hierarchical World Knowledge Model with Visual Keypoint Enhancement for Zero-Shot 3D Path Planning

    Sep 30, 2026Guoqing Ma, Mingqi Yuan, Chen Gao +2Zero-Shot Robotic ManipulationLanguage-Conditioned Robot Manipulation

  26. HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understanding

    Sep 29, 2026Hanwen Cao, Wenqiang Wu, Kuang-Ting Tu +5Implicit Neural RepresentationsHierarchical Representation Learning