mlsanityData to 14 Oct 2026

TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields

arXiv 2105.11605 ↗First posted 25 May 2021cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved promising results, existing solutions neglect the following aspects, which may cause performance degradation: (1) huge size difference between objects in outdoor scenes; (2) moving objects that are unrelated to place recognition; (3) long-range contextual information. We illustrate that the above aspects bring challenges to extracting discriminative global descriptors. To mitigate these problems, we propose a novel method named TransLoc3D, utilizing adaptive receptive fields with a point-wise reweighting scheme to handle objects of different sizes while suppressing noises, and an external transformer to capture long-range feature dependencies. As opposed to existing architectures which adopt fixed and limited receptive fields, our method benefits from size-adaptive receptive fields as well as global contextual information, and outperforms current state-of-the-arts with significant improvements on popular datasets.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 49 of its 71 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

49 of 71 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  12. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
37 more
  1. 2014Going Deeper with Convolutionscited by 4,241
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  7. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  9. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  10. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  11. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  12. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  13. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  14. 2020PCT: Point cloud transformercited by 732
  15. 2021Transformer in Transformercited by 633
  16. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  17. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  18. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  19. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  20. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  21. 2019Selective Kernel Networkscited by 403
  22. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  23. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  24. 2020A Metric Learning Reality Checkcited by 321
  25. 2017Sampling Matters in Deep Embedding Learningcited by 285
  26. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 198
  27. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  28. 2020MinkLoc3D: Point Cloud Based Large-Scale Place Recognitioncited by 115
  29. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  30. 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 100
  31. 2019PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrievalcited by 68
  32. 2020SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognitioncited by 66
  33. 2017Learnable pooling with Context Gating for video classificationcited by 58
  34. 2021MinkLoc++: Lidar and Monocular Image Fusion for Place Recognitioncited by 41
  35. 2021NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representationcited by 38
  36. 20173D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detectioncited by 35
  37. 2016Robust and Efficient Relative Pose with a Multi-camera System for Autonomous Vehicle in Highly Dynamic Environmentscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 5; 2024: 4; 2025: 9; 2026: 7.

29 papers.

Sort:

By area:

  1. 2022Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Trainingcited by 45
  2. 2023BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Imagescited by 39
  3. 2022CASSPR: Cross Attention Single Scan Place Recognitioncited by 22
  4. 2023I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projectionscited by 16
  5. 2021MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensitycited by 12
  6. 2023CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognitioncited by 10
  7. 2025CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Frameworkcited by 8
  8. 2025HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Viewscited by 8
  9. 2024Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environmentscited by 7
  10. 2024SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognitioncited by 7
  11. 2024MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutionscited by 6
  12. 2025ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Imagescited by 6
17 more
  1. 2025HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forestscited by 3
  2. 2022Uncertainty-Aware Lidar Place Recognition in Novel Environmentscited by 2
  3. 2023SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognitioncited by 2
  4. 2025Vehicle-Scene Interaction: A Text-Driven 3D Lidar Place Recognition Method for Autonomous Drivingcited by 2
  5. 2023VNI-Net: Vector Neurons-based Rotation-Invariant Descriptor for LiDAR Place Recognitioncited by 1
  6. 2025Ranking-aware Continual Learning for LiDAR Place Recognitioncited by 1
  7. 2025MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensitycited by 1
  8. 2025M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environmentscited by 1
  9. 2026SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localizationcited by 1
  10. 2026TreeLoc: 6-DoF LiDAR Global Localization in Forests via Inter-Tree Geometric Matchingcited by 1
  11. 2026Riemannian and Symplectic Geometry for Hierarchical Text-Driven Place Recognitioncited by 1
  12. 2024A Deeper Look into Second-Order Feature Aggregation for LiDAR Place Recognitioncited by 0
  13. 2025Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognitioncited by 0
  14. 2026Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAMcited by 0
  15. 2026Voronoi-based Second-order Descriptor with Whitened Metric in LiDAR Place Recognitioncited by 0
  16. 20264DRaL: Bridging 4D Radar with LiDAR for Place Recognition using Knowledge Distillationcited by 0
  17. 2026DTIF: Robust Loop Closure Detection via Delaunay Triangle Topology in Complex Forestscited by 0