mlsanityData to 14 Oct 2026

BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds

arXiv 2310.17281 ↗First posted 26 Oct 2023cs.CV cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds. We design a contrastive loss between features of Lidar scans captured in the same scene. Several such approaches have been proposed in the literature from PointConstrast, which uses a contrast at the level of points, to the state-of-the-art TARL, which uses a contrast at the level of segments, roughly corresponding to objects. While the former enjoys a great simplicity of implementation, it is surpassed by the latter, which however requires a costly pre-processing. In BEVContrast, we define our contrast at the level of 2D cells in the Bird's Eye View plane. Resulting cell-level representations offer a good trade-off between the point-level representations exploited in PointContrast and segment-level representations exploited in TARL: we retain the simplicity of PointContrast (cell representations are cheap to compute) while surpassing the performance of TARL in downstream semantic segmentation.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

32 of 45 references.

References · 32

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  12. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
20 more
  1. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  2. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  3. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  4. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  5. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  6. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  7. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  8. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  9. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  10. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  11. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  12. 2020OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learningcited by 65
  13. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 58
  14. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  15. 2021SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representationscited by 55
  16. 2023Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Losscited by 35
  17. 2021Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretrainingcited by 33
  18. 2021Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensorcited by 29
  19. 2023Spatiotemporal Self-supervised Learning for Point Clouds in the Wildcited by 23
  20. 2022Boosting Point-BERT by Multi-choice Tokenscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 9; 2025: 13; 2026: 1.

24 papers.

Sort:

By area:

  1. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 33
  2. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  3. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  4. 2024VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Drivingcited by 15
  5. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  6. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 12
  7. 2025Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapterscited by 9
  8. 2025TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Predictioncited by 9
  9. 2024Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perceptioncited by 8
  10. 2024Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibrationcited by 7
  11. 2023Prospective Role of Foundation Models in Advancing Autonomous Vehiclescited by 7
  12. 2025Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representationscited by 7
12 more
  1. 2024UNIT: Unsupervised Online Instance Segmentation through Timecited by 5
  2. 2024S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Drivingcited by 4
  3. 2025Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretrainingcited by 4
  4. 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Drivingcited by 4
  5. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  6. 2025PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Cloudscited by 3
  7. 2026DriveZero: End-to-End Driving Beyond Human Demonstrationscited by 3
  8. 2025Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baselinecited by 1
  9. 2024MILAN: Milli-Annotations for Lidar Semantic Segmentationcited by 0
  10. 2025Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentationcited by 0
  11. 2025S-BEVLoc: BEV-based Self-supervised Framework for Large-scale LiDAR Global Localizationcited by 0
  12. 20253D sans 3D Scans: Scalable Pre-training from Video-Generated Point Cloudscited by 0