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

arXiv: https://arxiv.org/abs/2310.17281 · HTML: https://mlsanity.com/paper/2310.17281/

## 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 (most cited first, 30 of 32)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Self-supervised Learning of Point Clouds via Orientation Estimation](https://mlsanity.com/paper/2008.00305/) (2020)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning](https://mlsanity.com/paper/2012.11552/) (2020)
- [Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders](https://mlsanity.com/paper/2206.09900/) (2022)
- [GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds](https://mlsanity.com/paper/2212.03010/) (2022)
- [SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations](https://mlsanity.com/paper/2112.04680/) (2021)
- [Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss](https://mlsanity.com/paper/2301.05709/) (2023)
- [Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining](https://mlsanity.com/paper/2104.04687/) (2021)
- [Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor](https://mlsanity.com/paper/2108.05560/) (2021)

## Built on by (most cited first, 24 of 24)

- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities](https://mlsanity.com/paper/2401.08045/) (2024)
- [LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes](https://mlsanity.com/paper/2501.04004/) (2025)
- [VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2411.14716/) (2024)
- [An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models](https://mlsanity.com/paper/2405.14870/) (2024)
- [LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving](https://mlsanity.com/paper/2501.04005/) (2025)
- [Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapters](https://mlsanity.com/paper/2503.03299/) (2025)
- [TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction](https://mlsanity.com/paper/2508.04682/) (2025)
- [Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception](https://mlsanity.com/paper/2405.07201/) (2024)
- [Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration](https://mlsanity.com/paper/2401.12452/) (2024)
- [Prospective Role of Foundation Models in Advancing Autonomous Vehicles](https://mlsanity.com/paper/2405.02288/) (2023)
- [Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations](https://mlsanity.com/paper/2507.05260/) (2025)
- [UNIT: Unsupervised Online Instance Segmentation through Time](https://mlsanity.com/paper/2409.07887/) (2024)
- [S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving](https://mlsanity.com/paper/2410.23085/) (2024)
- [Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining](https://mlsanity.com/paper/2503.19912/) (2025)
- [SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving](https://mlsanity.com/paper/2509.16588/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds](https://mlsanity.com/paper/2503.13914/) (2025)
- [DriveZero: End-to-End Driving Beyond Human Demonstrations](https://mlsanity.com/paper/2609.06055/) (2026)
- [Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline](https://mlsanity.com/paper/2503.13203/) (2025)
- [MILAN: Milli-Annotations for Lidar Semantic Segmentation](https://mlsanity.com/paper/2407.15797/) (2024)
- [Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation](https://mlsanity.com/paper/2503.07167/) (2025)
- [S-BEVLoc: BEV-based Self-supervised Framework for Large-scale LiDAR Global Localization](https://mlsanity.com/paper/2509.09110/) (2025)
- [3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds](https://mlsanity.com/paper/2512.23042/) (2025)

## 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.