mlsanityData to 14 Oct 2026

BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR

arXiv 2206.15154 ↗First posted 30 Jun 2022cs.CV cs.ROcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper is about extremely robust and lightweight localisation using LiDAR point clouds based on instance segmentation and graph matching. We model 3D point clouds as fully-connected graphs of semantically identified components where each vertex corresponds to an object instance and encodes its shape. Optimal vertex association across graphs allows for full 6-Degree-of-Freedom (DoF) pose estimation and place recognition by measuring similarity. This representation is very concise, condensing the size of maps by a factor of 25 against the state-of-the-art, requiring only 3kB to represent a 1.4MB laser scan. We verify the efficacy of our system on the SemanticKITTI dataset, where we achieve a new state-of-the-art in place recognition, with an average of 88.4% recall at 100% precision where the next closest competitor follows with 64.9%. We also show accurate metric pose estimation performance - estimating 6-DoF pose with median errors of 10 cm and 0.33 deg.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 30 Jun 2022.

Builds on

15 of 31 references.

References · 15

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  4. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 198
  5. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  6. 2016SegMatch: Segment based loop-closure for 3D point cloudscited by 48
  7. 2020Semantic Graph Based Place Recognition for 3D Point Cloudscited by 43
  8. 2019SegMap: Segment-based mapping and localization using data-driven descriptorscited by 42
  9. 2019LiDAR Iris for Loop-Closure Detectioncited by 39
  10. 2020Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Poolingcited by 38
  11. 2020Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detectioncited by 37
  12. 2021SSC: Semantic Scan Context for Large-Scale Place Recognitioncited by 24
3 more
  1. 2021SemSegMap- 3D Segment-Based Semantic Localizationcited by 10
  2. 2021PSE-Match: A Viewpoint-free Place Recognition Method with Parallel Semantic Embeddingcited by 6
  3. 2020LiDAR Lateral Localisation Despite Challenging Occlusion from Trafficcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 2; 2026: 1.

10 papers.

  1. 2023G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Modelcited by 11
  2. 2023Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimationcited by 8
  3. 2024MSSPlace: Multi-Sensor Place Recognition with Visual and Text Semanticscited by 7
  4. 2023SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attentioncited by 5
  5. 2024That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisationcited by 3
  6. 2025REGRACE: A Robust and Efficient Graph-based Re-localization Algorithm using Consistency Evaluationcited by 2
  7. 2024Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Datacited by 1
  8. 2024QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitivescited by 1
  9. 2025Introspection in Learned Semantic Scene Graph Localisationcited by 0
  10. 2026Scene Representation using 360deg Saliency Graph and its Application in Vision-based Indoor Navigationcited by 0