# Three Pillars improving Vision Foundation Model Distillation for Lidar

arXiv: https://arxiv.org/abs/2310.17504 · HTML: https://mlsanity.com/paper/2310.17504/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 85 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 30 of 68)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [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)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [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)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [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)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [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)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)

## Built on by (most cited first, 30 of 44)

- [Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2405.05258/) (2024)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation](https://mlsanity.com/paper/2503.18944/) (2025)
- [LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models](https://mlsanity.com/paper/2504.14032/) (2025)
- [OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks](https://mlsanity.com/paper/2404.14027/) (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)
- [SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding](https://mlsanity.com/paper/2505.22643/) (2025)
- [Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapters](https://mlsanity.com/paper/2503.03299/) (2025)
- [Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration](https://mlsanity.com/paper/2401.12452/) (2024)
- [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)
- [Zero-Shot 4D Lidar Panoptic Segmentation](https://mlsanity.com/paper/2504.00848/) (2025)
- [TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models](https://mlsanity.com/paper/2403.11691/) (2024)
- [Valeo4Cast: A Modular Approach to End-to-End Forecasting](https://mlsanity.com/paper/2406.08113/) (2024)
- [UNIT: Unsupervised Online Instance Segmentation through Time](https://mlsanity.com/paper/2409.07887/) (2024)
- [LOSC: LiDAR Open-voc Segmentation Consolidator](https://mlsanity.com/paper/2507.07605/) (2025)
- [AnyThermal: Towards Learning Universal Representations for Thermal Perception](https://mlsanity.com/paper/2602.06203/) (2026)
- [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)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [OE3DIS: Open-Ended 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/2408.11747/) (2024)
- [Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?](https://mlsanity.com/paper/2412.08973/) (2024)
- [CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation](https://mlsanity.com/paper/2503.09878/) (2025)
- [Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2408.11280/) (2024)
- [Matryoshka Model Learning for Improved Elastic Student Models](https://mlsanity.com/paper/2505.23337/) (2025)
- [Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift](https://mlsanity.com/paper/2511.17455/) (2025)
- [Polar Perspectives: Evaluating 2-D LiDAR Projections for Robust Place Recognition with Visual Foundation Models](https://mlsanity.com/paper/2512.02897/) (2025)
- [R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation](https://mlsanity.com/paper/2601.07692/) (2026)
- [Label-Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2503.02372/) (2025)

## Abstract (arXiv)

Self-supervised image backbones can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervision. Ideally, 3D backbones for lidar should be able to inherit these properties after distillation of these powerful 2D features. The most recent methods for image-to-lidar distillation on autonomous driving data show promising results, obtained thanks to distillation methods that keep improving. Yet, we still notice a large performance gap when measuring the quality of distilled and fully supervised features by linear probing. In this work, instead of focusing only on the distillation method, we study the effect of three pillars for distillation: the 3D backbone, the pretrained 2D backbones, and the pretraining dataset. In particular, thanks to our scalable distillation method named ScaLR, we show that scaling the 2D and 3D backbones and pretraining on diverse datasets leads to a substantial improvement of the feature quality. This allows us to significantly reduce the gap between the quality of distilled and fully-supervised 3D features, and to improve the robustness of the pretrained backbones to domain gaps and perturbations.