用原型和系数联合预测，3D点云实例分割更快更稳。
ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Method
- 并行学习原型与系数，通过稀疏点采样构建多尺度特征
- 推理时间标准差仅1.0%，比当前最优方法低超10倍
- 在S3DIS和PartNet上均超越现有方法，速度提升28%
3D实例分割对理解点云场景至关重要。本文提出一种新型神经网络架构，用于点云实例分割。通过并行学习系数与原型，并将其组合生成实例预测。系数利用带有新多尺度模块（称为膨胀点内生模块）的过完备采样点集计算。由于获得的实例掩码预测集合是过完备的，采用非极大值抑制算法提取最终预测。该方法避免了耗时的聚类步骤，使推理时间更稳定。所提方法不仅比当前最优方法快28%，且推理时间标准差最低。实验表明，其推理时间标准差仅为总时间的1.0%，而当前最优方法在10.8%至53.1%之间。此外，本方法在S3DIS-blocks（Fold-5上mRec提升4.9%）和PartNet（平均mAP提升2.0%）上均优于现有方法。
原文摘要 · Abstract (English)
3D instance segmentation is crucial for obtaining an understanding of a point cloud scene. This paper presents a novel neural network architecture for performing instance segmentation on 3D point clouds. We propose to jointly learn coefficients and prototypes in parallel which can be combined to obtain the instance predictions. The coefficients are computed using an overcomplete set of sampled points with a novel multi-scale module, dubbed dilated point inception. As the set of obtained instance mask predictions is overcomplete, we employ a non-maximum suppression algorithm to retrieve the final predictions. This approach allows to omit the time-expensive clustering step and leads to a more stable inference time. The proposed method is not only 28% faster than the state-of-the-art, it also exhibits the lowest standard deviation. Our experiments have shown that the standard deviation of the inference time is only 1.0% of the total time while it ranges between 10.8 and 53.1% for the state-of-the-art methods. Lastly, our method outperforms the state-of-the-art both on S3DIS-blocks (4.9% in mRec on Fold-5) and PartNet (2.0% on average in mAP).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。