Semantic segmentation and instance segmentation based on 3D point clouds involve significant challenges, specifically in the task of joint semantic and instance segmentation. The efficient and effective mutual assistance between semantic and instance segmentation is rarely considered and still remains an unaddressed research problem. To address this, herein, a novel and robust 3D point cloud segmentation framework employing hierarchical coupled feature selection, named HCFS3D, is proposed; this framework can jointly and reciprocally perform semantic and instance segmentation. The framework is designed to promote these two tasks to exploit beneficial information from each other, on a shallow as well as a deep level. Moreover, to prevent the network from overfitting and to improve performance, we designed a loss function called the Adaptive Smooth Loss, which can adaptively assign different weights to samples that are difficult to segment. Furthermore, joint semantic and instance conditional random fields are included in the proposed framework to further improve its performance. Extensive experiments based on different datasets and various backbone networks demonstrate that HCFS3D outperforms other state-of-the-art methods.

基于3D点云的语义分割和实例分割涉及重大挑战，特别是在联合语义和实例分割的任务中。语义和实例分割之间的高效互助很少被考虑，并且仍然是一个尚未解决的研究问题。为了解决这个问题，在本文中，提出了一种新颖的，健壮的，采用分级耦合特征选择的3D点云分割框架，称为HCFS3D。该框架可以共同和相互执行语义和实例分割。该框架旨在促进这两项任务，以在浅层和深层上相互利用有益的信息。此外，为了防止网络过度安装并提高性能，我们设计了一种称为“自适应平滑损耗”的损耗函数，该函数可以为难以分割的样本自适应地分配不同的权重。此外，在所提出的框架中包括联合语义和实例条件随机字段，以进一步提高其性能。基于不同数据集和各种骨干网络的广泛实验表明，HCFS3D优于其他最新方法。