# Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving

arXiv: https://arxiv.org/abs/2405.05258 · HTML: https://mlsanity.com/paper/2405.05258/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 84 of its 115 references that are in the map.
- First posted on arXiv 8 May 2024.

## Builds on (most cited first, 30 of 84)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [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)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)

## Built on by (most cited first, 30 of 54)

- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving](https://mlsanity.com/paper/2405.17426/) (2024)
- [MemVerse: Multimodal Memory for Lifelong Learning Agents](https://mlsanity.com/paper/2512.03627/) (2025)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [Is Your HD Map Constructor Reliable under Sensor Corruptions?](https://mlsanity.com/paper/2406.12214/) (2024)
- [EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler](https://mlsanity.com/paper/2504.09540/) (2025)
- [The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition](https://mlsanity.com/paper/2405.08816/) (2024)
- [StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving](https://mlsanity.com/paper/2506.23982/) (2025)
- [LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes](https://mlsanity.com/paper/2501.04004/) (2025)
- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences](https://mlsanity.com/paper/2508.03692/) (2025)
- [SafeMap: Robust HD Map Construction from Incomplete Observations](https://mlsanity.com/paper/2507.00861/) (2025)
- [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)
- [3EED: Ground Everything Everywhere in 3D](https://mlsanity.com/paper/2511.01755/) (2025)
- [FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies](https://mlsanity.com/paper/2412.06708/) (2024)
- [SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding](https://mlsanity.com/paper/2505.22643/) (2025)
- [La La LiDAR: Large-Scale Layout Generation from LiDAR Data](https://mlsanity.com/paper/2508.03691/) (2025)
- [Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos](https://mlsanity.com/paper/2504.14921/) (2025)
- [How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation](https://mlsanity.com/paper/2505.18956/) (2025)
- [4D Driving Scene Generation With Stereo Forcing](https://mlsanity.com/paper/2509.20251/) (2025)
- [Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field](https://mlsanity.com/paper/2502.16303/) (2025)
- [Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations](https://mlsanity.com/paper/2507.05260/) (2025)
- [U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences](https://mlsanity.com/paper/2512.02982/) (2025)
- [Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras](https://mlsanity.com/paper/2507.17664/) (2025)
- [ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting](https://mlsanity.com/paper/2509.22225/) (2025)
- [Veila: Panoramic LiDAR Generation from a Monocular RGB Image](https://mlsanity.com/paper/2508.03690/) (2025)
- [Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining](https://mlsanity.com/paper/2503.19912/) (2025)
- [PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector](https://mlsanity.com/paper/2504.03563/) (2025)

## Abstract (arXiv)

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into semi-supervised learning for LiDAR semantic segmentation, leveraging the intrinsic spatial priors of driving scenes and multi-sensor complements to augment the efficacy of unlabeled datasets. We introduce LaserMix++, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to further assist data-efficient learning. Our framework is tailored to enhance 3D scene consistency regularization by incorporating multi-modality, including 1) multi-modal LaserMix operation for fine-grained cross-sensor interactions; 2) camera-to-LiDAR feature distillation that enhances LiDAR feature learning; and 3) language-driven knowledge guidance generating auxiliary supervisions using open-vocabulary models. The versatility of LaserMix++ enables applications across LiDAR representations, establishing it as a universally applicable solution. Our framework is rigorously validated through theoretical analysis and extensive experiments on popular driving perception datasets. Results demonstrate that LaserMix++ markedly outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations and significantly improving the supervised-only baselines. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.