mlsanityData to 14 Oct 2026

Text2Loc: 3D Point Cloud Localization from Natural Language

arXiv 2311.15977 ↗First posted 27 Nov 2023cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of 3D point cloud localization based on a few natural linguistic descriptions and introduce a novel neural network, Text2Loc, that fully interprets the semantic relationship between points and text. Text2Loc follows a coarse-to-fine localization pipeline: text-submap global place recognition, followed by fine localization. In global place recognition, relational dynamics among each textual hint are captured in a hierarchical transformer with max-pooling (HTM), whereas a balance between positive and negative pairs is maintained using text-submap contrastive learning. Moreover, we propose a novel matching-free fine localization method to further refine the location predictions, which completely removes the need for complicated text-instance matching and is lighter, faster, and more accurate than previous methods. Extensive experiments show that Text2Loc improves the localization accuracy by up to 2× over the state-of-the-art on the KITTI360Pose dataset. Our project page is publicly available at urlhttps://yan-xia.github.io/projects/text2loc/.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

29 of 43 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  7. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  8. 2022Planning-oriented Autonomous Drivingcited by 1,087
  9. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  10. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  11. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 452
  12. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 198
17 more
  1. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  2. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 141
  3. 2020MinkLoc3D: Point Cloud Based Large-Scale Place Recognitioncited by 115
  4. 2014Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognitioncited by 111
  5. 2023OrienterNet: Visual Localization in 2D Public Maps with Neural Matchingcited by 84
  6. 2021Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloudcited by 81
  7. 2022OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognitioncited by 69
  8. 2020SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognitioncited by 66
  9. 2022Text2Pos: Text-to-Point-Cloud Cross-Modal Localizationcited by 40
  10. 2021NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representationcited by 38
  11. 2021SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognitioncited by 36
  12. 2022A Lightweight and Detector-free 3D Single Object Tracker on Point Cloudscited by 23
  13. 2022CASSPR: Cross Attention Single Scan Place Recognitioncited by 22
  14. 2023Text to Point Cloud Localization with Relation-Enhanced Transformercited by 20
  15. 2023NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localizationcited by 13
  16. 2020VPC-Net: Completion of 3D Vehicles from MLS Point Cloudscited by 11
  17. 2021AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognitioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 13; 2026: 14.

35 papers.

Sort:

By area:

  1. 2024Where am I? Cross-View Geo-localization with Natural Language Descriptionscited by 38
  2. 2024"Where am I?" Scene Retrieval with Languagecited by 15
  3. 2025CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Frameworkcited by 8
  4. 2024MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba Mechanismscited by 7
  5. 2024OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentationcited by 6
  6. 2025Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognitioncited by 6
  7. 2024VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognitioncited by 5
  8. 2025GOTPR: General Outdoor Text-based Place Recognition Using Scene Graph Retrieval with OpenStreetMapcited by 5
  9. 2024Explicit Interaction for Fusion-Based Place Recognitioncited by 4
  10. 2025CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representationcited by 4
  11. 2025A Review of 3D Object Detection with Vision-Language Modelscited by 4
  12. 2026VGGT-MPR: VGGT-Enhanced Multimodal Place Recognition in Autonomous Driving Environmentscited by 4
23 more
  1. 2026VLM-Loc: Localization in Point Cloud Maps via Vision-Language Modelscited by 4
  2. 2024Instance-free Text to Point Cloud Localization with Relative Position Awarenesscited by 3
  3. 2025L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagerycited by 2
  4. 2025Vehicle-Scene Interaction: A Text-Driven 3D Lidar Place Recognition Method for Autonomous Drivingcited by 2
  5. 2026LaVPR: Benchmarking Language and Vision for Place Recognitioncited by 2
  6. 2026Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Modelscited by 2
  7. 2026UNIGEOCLIP: Unified Geospatial Contrastive Learningcited by 2
  8. 2025RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learningcited by 1
  9. 2025TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimationcited by 1
  10. 2026SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localizationcited by 1
  11. 2026Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Frameworkcited by 1
  12. 2026Riemannian and Symplectic Geometry for Hierarchical Text-Driven Place Recognitioncited by 1
  13. 2026DialogueVPR: Towards Conversational Visual Place Recognitioncited by 1
  14. 2024Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigationcited by 0
  15. 2025Introspection in Learned Semantic Scene Graph Localisationcited by 0
  16. 2025Text2Loc++: Generalizing 3D Point Cloud Localization from Natural Languagecited by 0
  17. 2025Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognitioncited by 0
  18. 2025Text2Graph VPR: A Text-to-Graph Expert System for Explainable Place Recognition in Changing Environmentscited by 0
  19. 2026Uncertainty-Aware Hierarchical Re-Localization in OpenStreetMap via Semantic Alignmentcited by 0
  20. 2026TOL: Textual Localization with OpenStreetMapcited by 0
  21. 2026G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognitioncited by 0
  22. 2026Trajectory-aware Cross-view Geo-localization with Sequential Observationscited by 0
  23. 2026PosEviLoc: Position-Conditioned Spatial Evidence for Language-Based 3D Localizationcited by 0