# MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training

arXiv: https://arxiv.org/abs/2303.13510 · HTML: https://mlsanity.com/paper/2303.13510/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 53 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [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)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [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)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)

## Built on by (most cited first, 26 of 26)

- [UniPAD: A Universal Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2310.08370/) (2023)
- [MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations](https://mlsanity.com/paper/2311.11762/) (2023)
- [AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset](https://mlsanity.com/paper/2306.00612/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection](https://mlsanity.com/paper/2501.04969/) (2025)
- [UniM2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving](https://mlsanity.com/paper/2308.10421/) (2023)
- [T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning](https://mlsanity.com/paper/2312.10217/) (2023)
- [MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2401.16305/) (2024)
- [Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration](https://mlsanity.com/paper/2401.12452/) (2024)
- [Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds](https://mlsanity.com/paper/2502.20316/) (2025)
- [SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations](https://mlsanity.com/paper/2309.10527/) (2023)
- [Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensing](https://mlsanity.com/paper/2406.07833/) (2024)
- [Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges](https://mlsanity.com/paper/2502.02692/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation](https://mlsanity.com/paper/2305.15213/) (2023)
- [Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection](https://mlsanity.com/paper/2404.11737/) (2024)
- [Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection](https://mlsanity.com/paper/2408.03790/) (2024)
- [TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception](https://mlsanity.com/paper/2412.03054/) (2024)
- [JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data](https://mlsanity.com/paper/2503.08422/) (2025)
- [Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception](https://mlsanity.com/paper/2405.17942/) (2024)
- [Exploring the Untouched Sweeps for Conflict-Aware 3D Segmentation Pretraining](https://mlsanity.com/paper/2407.07465/) (2024)
- [CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning](https://mlsanity.com/paper/2412.03059/) (2024)
- [Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal](https://mlsanity.com/paper/2603.28224/) (2026)
- [M3CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders](https://mlsanity.com/paper/2309.13235/) (2023)
- [Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps](https://mlsanity.com/paper/2410.01319/) (2024)
- [Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation](https://mlsanity.com/paper/2503.07167/) (2025)

## Abstract (arXiv)

This paper introduces the Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset. Inspired by the scene-voxel-point hierarchy in downstream 3D object detectors, we design masking and reconstruction strategies accounting for voxel distributions in the scene and local point distributions within the voxel. We employ a Reversed-Furthest-Voxel-Sampling strategy to address the uneven distribution of LiDAR points and propose MV-JAR, which combines two techniques for modeling the aforementioned distributions, resulting in superior performance. Our experiments reveal limitations in previous data-efficient experiments, which uniformly sample fine-tuning splits with varying data proportions from each LiDAR sequence, leading to similar data diversity across splits. To address this, we propose a new benchmark that samples scene sequences for diverse fine-tuning splits, ensuring adequate model convergence and providing a more accurate evaluation of pre-training methods. Experiments on our Waymo benchmark and the KITTI dataset demonstrate that MV-JAR consistently and significantly improves 3D detection performance across various data scales, achieving up to a 6.3% increase in mAPH compared to training from scratch. Codes and the benchmark will be available at https://github.com/SmartBot-PJLab/MV-JAR .