论文标题
共同实例和语义分割点云的自我预测
Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds
论文作者
论文摘要
我们开发了一种新颖的学习方案，称为3D实例的自我预测和点云的语义分割。与大多数专注于设计卷积操作员的现有方法不同，我们的方法设计了一种新的学习方案，以增强点关系探索以更好地细分。更具体地说，我们将点云样本分为两个子集，并根据其表示形式构造完整的图。然后，我们使用标签传播算法来预测一个子集的标签，当给出另一个子集的标签时。通过通过这项自我预测任务进行培训，骨干网络被限制以完全探索关系上下文/几何/形状信息，并学习更多的判别特征以进行分割。此外，配备我们自我预测方案的一般关联框架旨在同时增强实例和语义分割，其中实例和语义表示结合以执行自我预测。通过这种方式，实例和语义细分进行了协作和相互加强。与基线相比，在S3DIS和Shapenet上获得了显着的性能改进和语义细分。与S3DIS和Shapenet上的最新艺术相比，我们的方法在S3DIS和可比较的语义分割结果上获得了最新的实例分割结果，而我们仅将PointNet ++作为骨干网络。
We develop a novel learning scheme named Self-Prediction for 3D instance and semantic segmentation of point clouds. Distinct from most existing methods that focus on designing convolutional operators, our method designs a new learning scheme to enhance point relation exploring for better segmentation. More specifically, we divide a point cloud sample into two subsets and construct a complete graph based on their representations. Then we use label propagation algorithm to predict labels of one subset when given labels of the other subset. By training with this Self-Prediction task, the backbone network is constrained to fully explore relational context/geometric/shape information and learn more discriminative features for segmentation. Moreover, a general associated framework equipped with our Self-Prediction scheme is designed for enhancing instance and semantic segmentation simultaneously, where instance and semantic representations are combined to perform Self-Prediction. Through this way, instance and semantic segmentation are collaborated and mutually reinforced. Significant performance improvements on instance and semantic segmentation compared with baseline are achieved on S3DIS and ShapeNet. Our method achieves state-of-the-art instance segmentation results on S3DIS and comparable semantic segmentation results compared with state-of-the-arts on S3DIS and ShapeNet when we only take PointNet++ as the backbone network.
