论文标题
用于点云上3D实例分割的软组
SoftGroup for 3D Instance Segmentation on Point Clouds
论文作者
论文摘要
现有的最新3D实例分割方法执行语义细分，然后进行分组。执行语义分割时会做出硬预测，以使每个点都与单个类关联。但是，由于艰难的决定而引起的错误繁殖到分组中，导致（1）预测的实例与地面真理和（2）实质性误报之间的重叠。为了解决上述问题，本文提出了一种3D实例分割方法，称为软组，通过执行自下而上的软组分组，然后进行自上而下的细化。软组允许每个点与多个类相关联，以减轻来自语义预测错误的问题，并通过学习将它们分类为背景来抑制误报实例。在不同数据集和多个评估指标上的实验结果证明了软组的功效。其性能超过了最强的先验方法，在Scannet V2隐藏测试集上的显着余量为 +6.2％，而S3DIS区域5的 +6.8％的差距为AP_50。软组也很快，每次扫描以345毫秒的运行，在扫描仪V2数据集上使用单个Titan X运行。两个数据集的源代码和训练有素的模型均可在\ url {https://github.com/thangvubk/softgroup.git}上获得。
Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation such that each point is associated with a single class. However, the errors stemming from hard decision propagate into grouping that results in (1) low overlaps between the predicted instance with the ground truth and (2) substantial false positives. To address the aforementioned problems, this paper proposes a 3D instance segmentation method referred to as SoftGroup by performing bottom-up soft grouping followed by top-down refinement. SoftGroup allows each point to be associated with multiple classes to mitigate the problems stemming from semantic prediction errors and suppresses false positive instances by learning to categorize them as background. Experimental results on different datasets and multiple evaluation metrics demonstrate the efficacy of SoftGroup. Its performance surpasses the strongest prior method by a significant margin of +6.2% on the ScanNet v2 hidden test set and +6.8% on S3DIS Area 5 in terms of AP_50. SoftGroup is also fast, running at 345ms per scan with a single Titan X on ScanNet v2 dataset. The source code and trained models for both datasets are available at \url{https://github.com/thangvubk/SoftGroup.git}.
