Dense prediction tasks are common for 3D point clouds, but the inherent uncertainties in massive points and their embeddings have long been ignored. In this work, we present CUE, a novel uncertainty estimation method for dense prediction tasks of 3D point clouds. Inspired by metric learning, the key idea of CUE is to explore cross-point embeddings upon a conventional dense prediction pipeline. Specifically, CUE involves building a probabilistic embedding model and then enforcing metric alignments of massive points in the embedding space. We demonstrate that CUE is a generic and effective tool for dense uncertainty estimation of 3D point clouds in two different tasks: (1) in 3D geometric feature learning we for the first time obtain well-calibrated dense uncertainty, and (2) in semantic segmentation we reduce uncertainty`s Expected Calibration Error of the state-of-the-arts by 43.8%. All uncertainties are estimated without compromising predictive performance.

翻译：3D点云的频繁预测任务很常见,但大型点及其嵌入的内在不确定性长期以来一直被忽视。在这项工作中,我们介绍了三D点云密集预测任务的新颖的不确定性估计方法CUE。在光学学习的启发下,CUE的关键想法是探索将交叉点嵌入常规密集预测管道。具体地说,CUE涉及建立一个概率嵌入模型,然后对嵌入空间的大型点进行量性调整。我们证明,CUE是两种不同任务对3D点云进行密集不确定性估计的通用有效工具:(1) 在3D几何特征学中,我们第一次获得精确的密度不确定性,(2) 在语义分化中,我们将不确定性的预测“状态的校准错误”减少43.8%。所有不确定性都是在不影响预测性能的情况下估算的。