mlsanityData to 7 Oct 2026

2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloud

arXiv 1904.09742 ↗First posted 22 Apr 2019cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart. However, it is seldom used in visual pose estimation due to the difficulty in obtaining 2D-3D image to point cloud correspondences. In this paper, we propose the 2D3D-MatchNet - an end-to-end deep network architecture to jointly learn the descriptors for 2D and 3D keypoint from image and point cloud, respectively. As a result, we are able to directly match and establish 2D-3D correspondences from the query image and 3D point cloud reference map for visual pose estimation. We create our Oxford 2D-3D Patches dataset from the Oxford Robotcar dataset with the ground truth camera poses and 2D-3D image to point cloud correspondences for training and testing the deep network. Experimental results verify the feasibility of our approach.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 18; 2024: 14; 2025: 8; 2026: 11.

62 papers.

Sort:

By area:

  1. 2021DeepI2P: Image-to-Point Cloud Registration via Deep Classificationcited by 58
  2. 2022CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondencecited by 43
  3. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  4. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 35
  5. 2023FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimatorscited by 29
  6. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  7. 2023LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localizationcited by 26
  8. 2023(LC)2: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognitioncited by 16
  9. 2023I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projectionscited by 15
  10. 20233DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4Vcited by 15
  11. 2024CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibrationcited by 15
  12. 2021i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditionscited by 14
38 more
  1. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  2. 2025Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignmentcited by 14
  3. 2024Looking 3D: Anomaly Detection with 2D-3D Alignmentcited by 13
  4. 2023CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registrationcited by 12
  5. 2023E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learningcited by 11
  6. 2023End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localizationcited by 9
  7. 2021Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learningcited by 8
  8. 2023EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localizationcited by 8
  9. 2025CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selectioncited by 8
  10. 2025Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Priorcited by 8
  11. 2024VOLoc: Visual Place Recognition by Querying Compressed Lidar Mapcited by 7
  12. 2022Extrinsic Camera Calibration with Semantic Segmentationcited by 6
  13. 2025Adaptive Agent Selection and Interaction Network for Image-to-point cloud Registrationcited by 6
  14. 2022Contrastive Learning of Features between Images and LiDARcited by 5
  15. 2024ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognitioncited by 5
  16. 2023Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networkscited by 4
  17. 2023Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registrationcited by 4
  18. 2024VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognitioncited by 4
  19. 2024Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matchingcited by 4
  20. 2024CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registrationcited by 3
  21. 2025EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point Cloudscited by 3
  22. 2021Multimodal Colored Point Cloud to Image Alignmentcited by 2
  23. 2023Automated Static Camera Calibration with Intelligent Vehiclescited by 2
  24. 2023On the Localization of Ultrasound Image Slices within Point Distribution Modelscited by 2
  25. 2024TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenescited by 2
  26. 2022Uncertainty-Aware DNN for Multi-Modal Camera Localizationcited by 1
  27. 2022Attention-Enhanced Cross-modal Localization Between 360 Images and Point Cloudscited by 1
  28. 2023Deep Learning in Healthcare: An In-Depth Analysiscited by 1
  29. 2024EEPNet: Efficient Edge Pixel-based Matching Network for Cross-Modal Dynamic Registration between LiDAR and Cameracited by 1
  30. 2026GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registrationcited by 1
  31. 2026Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphscited by 1
  32. 2022Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondencescited by 0
  33. 2023Single-Shot Global Localization via Graph-Theoretic Correspondence Matchingcited by 0
  34. 2024Towards Zero-Shot Interpretable Human Recognition: A 2D-3D Registration Frameworkcited by 0
  35. 2024MaFreeI2P: A Matching-Free Image-to-Point Cloud Registration Paradigm with Active Camera Pose Retrievalcited by 0
  36. 2024SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registrationcited by 0
  37. 2024TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registrationcited by 0
  38. 2024Cross-Modal Visual Relocalization in Prior LiDAR Maps Utilizing Intensity Texturescited by 0

50 most cited of 62 All 62 (JSON)