SALT让激光雷达点云自动标注更高效，跨场景一致且支持时序连续性。
SALT: A Flexible Semi-Automatic Labeling Tool for General LiDAR Point Clouds with Cross-Scene Adaptability and 4D Consistency
- 直接处理原始点云，用数据对齐生成伪图像实现零样本分割。
- 在SemanticKITTI上比最新方法高18.4%的PQ，接近人工标注50%性能。
- 适合需要快速标注多场景、多时间维度激光雷达数据的研究者。
我们提出一种灵活的半自动标注工具SALT，适用于通用激光雷达点云，具备跨场景适应性和4D一致性。与依赖相机蒸馏的现有方法不同，SALT直接作用于原始激光雷达数据，自动生成预分割结果。为此，我们提出一种新颖的零样本学习范式——数据对齐，通过将激光雷达数据与视觉基础模型的训练分布对齐，转化为伪图像。此外，设计了4D一致性提示策略和4D非极大值抑制模块，以增强SAM2，确保高质量且时间上一致的预分割。SALT在SemanticKITTI上比最新零样本方法高出18.4%的PQ；在新采集的低分辨率激光雷达数据及三种激光雷达类型组合数据上，达到接近人类标注者40-50%的性能，显著提升标注效率。我们预计开源SALT将推动当前激光雷达数据集的大幅扩展，并为未来激光雷达基础模型的发展奠定基础。代码已公开：https://github.com/Cavendish518/SALT。
原文摘要 · Abstract (English)
We propose a flexible Semi-Automatic Labeling Tool (SALT) for general LiDAR point clouds with cross-scene adaptability and 4D consistency. Unlike recent approaches that rely on camera distillation, SALT operates directly on raw LiDAR data, automatically generating pre-segmentation results. To achieve this, we propose a novel zero-shot learning paradigm, termed data alignment, which transforms LiDAR data into pseudo-images by aligning with the training distribution of vision foundation models. Additionally, we design a 4D-consistent prompting strategy and 4D non-maximum suppression module to enhance SAM2, ensuring high-quality, temporally consistent presegmentation. SALT surpasses the latest zero-shot methods by 18.4% PQ on SemanticKITTI and achieves nearly 40-50% of human annotator performance on our newly collected low-resolution LiDAR data and on combined data from three LiDAR types, significantly boosting annotation efficiency. We anticipate that SALT's open-sourcing will catalyze substantial expansion of current LiDAR datasets and lay the groundwork for the future development of LiDAR foundation models. Code is available at https://github.com/Cavendish518/SALT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。