UnO：用于感知与预测的无监督占据场
UnO: Unsupervised Occupancy Fields for Perception and Forecasting
AI总结：
本文提出 UnO，一种利用 LiDAR 自监督学习连续4D时空占据场的无监督世界模型，可迁移至点云、语义占据和几何占据预测并取得领先性能。
摘要：
感知世界并预测其未来状态是自动驾驶的一项关键任务。监督方法利用带标注的物体标签来学习世界模型——传统上采用物体检测和轨迹预测，或时序鸟瞰图（BEV）占据场。然而，这些标注成本高昂，且通常局限于一组预定义类别，无法涵盖我们在道路上可能遇到的所有事物。为此，我们通过来自 LiDAR 数据的自监督，学习感知并预测一个连续的4D（时空）占据场。这种无监督世界模型可以轻松且有效地迁移到下游任务。我们通过添加一个轻量级的学习渲染器来解决点云预测问题，并在 Argoverse 2、nuScenes 和 KITTI 上取得了最先进的性能。为进一步展示其可迁移性，我们将模型微调用于 BEV 语义占据预测，并表明其性能优于完全监督的最先进方法，尤其是在标注数据稀缺时。最后，在时空几何占据预测方面与此前的最先进方法相比，我们的4D世界模型对与自动驾驶相关类别的物体实现了高得多的召回率。
英文摘要：
Perceiving the world and forecasting its future state is a critical task for self-driving. Supervised approaches leverage annotated object labels to learn a model of the world -- traditionally with object detections and trajectory predictions, or temporal bird's-eye-view (BEV) occupancy fields. However, these annotations are expensive and typically limited to a set of predefined categories that do not cover everything we might encounter on the road. Instead, we learn to perceive and forecast a continuous 4D (spatio-temporal) occupancy field with self-supervision from LiDAR data. This unsupervised world model can be easily and effectively transferred to downstream tasks. We tackle point cloud forecasting by adding a lightweight learned renderer and achieve state-of-the-art performance in Argoverse 2, nuScenes, and KITTI. To further showcase its transferability, we fine-tune our model for BEV semantic occupancy forecasting and show that it outperforms the fully supervised state-of-the-art, especially when labeled data is scarce. Finally, when compared to prior state-of-the-art on spatio-temporal geometric occupancy prediction, our 4D world model achieves a much higher recall of objects from classes relevant to self-driving.
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。
