Instance segmentation on point clouds is crucially important for 3D scene understanding. Most SOTAs adopt distance clustering, which is typically effective but does not perform well in segmenting adjacent objects with the same semantic label (especially when they share neighboring points). Due to the uneven distribution of offset points, these existing methods can hardly cluster all instance points. To this end, we design a novel divide-and-conquer strategy named PBNet that binarizes each point and clusters them separately to segment instances. Our binary clustering divides offset instance points into two categories: high and low density points (HPs vs. LPs). Adjacent objects can be clearly separated by removing LPs, and then be completed and refined by assigning LPs via a neighbor voting method. To suppress potential over-segmentation, we propose to construct local scenes with the weight mask for each instance. As a plug-in, the proposed binary clustering can replace the traditional distance clustering and lead to consistent performance gains on many mainstream baselines. A series of experiments on ScanNetV2 and S3DIS datasets indicate the superiority of our model. In particular, PBNet achieves leading results on the ScanNetV2 official benchmark challenge, with a relative 5.4% and 4.9% mAP improvement on validation and test set respectively, compared with the SOTAs.
翻译:对于 3D 场景 理解 3D 场景 理解 。 大多数 SOTA 采用 远程集成, 通常有效, 但是在用同一语义标签分割相邻物体方面效果不佳, 特别是当它们共享相邻点时。 由于抵消点分布不均, 这些现有方法几乎不可能将所有实例点集中在一起。 为此, 我们设计了一个名为 PBNet 的新颖的分化和共解战略, 将每个点双向点分解, 将每个点分解成双向点, 我们的二进制组合将实例分解为两类: 高密度和低密度点( HPs v. LPs) 。 相近对象可以通过删除 LPs 来明确分离, 然后通过邻居投票方法指定 LPs 来完成和精细化。 为了抑制可能的超标, 我们建议用每个例子的重量遮盖来构建本地场景。 作为插件, 拟议的双向组合组合可以取代传统的远程集, 并导致许多主流基线上的业绩增益。 一系列关于 ScNS 和SARV2 的实验显示模型的优势, 。