mlsanityData to 7 Oct 2026

Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments

arXiv 2403.13395 ↗First posted 20 Mar 2024cs.CV cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

Perceptual aliasing and weak textures pose significant challenges to the task of place recognition, hindering the performance of Simultaneous Localization and Mapping (SLAM) systems. This paper presents a novel model, called UMF (standing for Unifying Local and Global Multimodal Features) that 1) leverages multi-modality by cross-attention blocks between vision and LiDAR features, and 2) includes a re-ranking stage that re-orders based on local feature matching the top-k candidates retrieved using a global representation. Our experiments, particularly on sequences captured on a planetary-analogous environment, show that UMF outperforms significantly previous baselines in those challenging aliased environments. Since our work aims to enhance the reliability of SLAM in all situations, we also explore its performance on the widely used RobotCar dataset, for broader applicability. Code and models are available at https://github.com/DLR-RM/UMF

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 31 of its 54 references that are in the map. First posted on arXiv 20 Mar 2024.

Builds on

31 of 54 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  7. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  8. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  9. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  10. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 236
  11. 2022Visual Attention Networkcited by 210
  12. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 197
19 more
  1. 2019The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Datasetcited by 133
  2. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  3. 2018The TUM VI Benchmark for Evaluating Visual-Inertial Odometrycited by 94
  4. 2023Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modelingcited by 92
  5. 2021Where is your place, Visual Place Recognition?cited by 82
  6. 2022OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognitioncited by 69
  7. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
  8. 20204Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Drivingcited by 51
  9. 2021MinkLoc++: Lidar and Monocular Image Fusion for Place Recognitioncited by 41
  10. 2022Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Cloudscited by 39
  11. 2021AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognitioncited by 36
  12. 2022Learning Super-Features for Image Retrievalcited by 35
  13. 2023Visual Place Recognition: A Tutorialcited by 31
  14. 2021TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fieldscited by 29
  15. 2018Attention-based Pyramid Aggregation Network for Visual Place Recognitioncited by 21
  16. 2019VIZARD: Reliable Visual Localization for Autonomous Vehicles in Urban Outdoor Environmentscited by 9
  17. 2022Challenges of SLAM in extremely unstructured environments: the DLR Planetary Stereo, Solid-State LiDAR, Inertial Datasetcited by 9
  18. 2020SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environmentcited by 6
  19. 20226D Camera Relocalization in Visually Ambiguous Extreme Environmentscited by 1

Built on by

Cited by year (2026 to 7 Oct)

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

7 papers.

  1. 2025UAVScenes: A Multi-Modal Dataset for UAVscited by 26
  2. 2024MSSPlace: Multi-Sensor Place Recognition with Visual and Text Semanticscited by 7
  3. 2024PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusioncited by 2
  4. 2025Multi-modal Loop Closure Detection with Foundation Models in Severely Unstructured Environmentscited by 2
  5. 2025M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environmentscited by 1
  6. 2026MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognitioncited by 0
  7. 2026M3GA-Wild: A Large-Scale Dataset and Benchmark for Multi-Modal Multi-session Ground-to-Aerial Place Recognition in Forestscited by 0