SPOT：通过占用预测进行可扩展3D预训练以学习可迁移的3D表示
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations
AI总结：
本文提出SPOT，通过占用预测进行3D点云预训练以学习可迁移表示，结合beam re-sampling和类平衡策略解决域差距，在多数据集和任务上展现强泛化与可扩展性。
摘要：
为感知任务标注3D LiDAR点云是自动驾驶等众多应用的基础，但仍然极其耗费人力。预训练-微调方法可以通过在各种下游数据集和任务中微调预训练主干网络来缓解标注负担。在本文中，我们提出了SPOT，即在这种标签高效的微调范式下，通过占用预测进行可扩展预训练以学习可迁移的3D表示。SPOT在具有不同下游任务的各种公共数据集上实现了有效性，展示了其通用表示能力、跨域鲁棒性和数据可扩展性，这是实际应用的三个关键因素。具体而言，我们首次在理论和经验上证明，可以通过占用预测任务实现通用表示学习。然后，为了解决由不同LiDAR传感器和标注方法引起的域差距，我们开发了一种用于点云增强的beam re-sampling技术，并结合了类平衡策略。此外，观察到了可扩展预训练，即随着预训练数据的增加，所有实验的下游性能都变得更好。此外，这种预训练策略也与未标记数据保持兼容。希望我们的发现能促进对LiDAR点的理解，并为LiDAR预训练的未来发展铺平道路。
英文摘要：
Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks. In this paper, we propose SPOT, namely Scalable Pre-training via Occupancy prediction for learning Transferable 3D representations under such a label-efficient fine-tuning paradigm. SPOT achieves effectiveness on various public datasets with different downstream tasks, showcasing its general representation power, cross-domain robustness and data scalability which are three key factors for real-world application. Specifically, we both theoretically and empirically show, for the first time, that general representations learning can be achieved through the task of occupancy prediction. Then, to address the domain gap caused by different LiDAR sensors and annotation methods, we develop a beam re-sampling technique for point cloud augmentation combined with class-balancing strategy. Furthermore, scalable pre-training is observed, that is, the downstream performance across all the experiments gets better with more pre-training data. Additionally, such pre-training strategy also remains compatible with unlabeled data. The hope is that our findings will facilitate the understanding of LiDAR points and pave the way for future advancements in LiDAR pre-training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
