We propose a novel, conceptually simple and general framework for instance
segmentation on 3D point clouds. Our method, called 3D-BoNet, follows the
simple design philosophy of per-point multilayer perceptrons (MLPs). The
framework directly regresses 3D bounding boxes for all instances in a point
cloud, while simultaneously predicting a point-level mask for each instance. It
consists of a backbone network followed by two parallel network branches for 1)
bounding box regression and 2) point mask prediction. 3D-BoNet is single-stage,
anchor-free and end-to-end trainable. Moreover, it is remarkably
computationally efficient as, unlike existing approaches, it does not require
any post-processing steps such as non-maximum suppression, feature sampling,
clustering or voting. Extensive experiments show that our approach surpasses
existing work on both ScanNet and S3DIS datasets while being approximately 10x
more computationally efficient. Comprehensive ablation studies demonstrate the
effectiveness of our design.

3D-BoNet 是一个新颖的、简单易懂且通用的网络，可在 3D 点云上实现实例分割。该网络由骨干网和两个并行支路（边界框回归和点掩码预测）组成，并在保持端到端训练的同时，直接回归点云中所有实例的 3D 边界框和每个实例的点级掩码。实验表明，相比现有方法，该方法不仅在 ScanNet 和 S3DIS 数据集上的表现更优，而且计算效率提高了约 10 倍，并且该算法的设计是有效的。