论文标题
Dyco3D：通过动态卷积对3D点云进行稳健实例分割
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
论文作者
论文摘要
点云实例分割的先前表现最佳方法涉及一种自下而上的策略，该策略通常包括效率低下的操作或复杂的管道，例如对过度分段的组件进行分组，引入了精炼或设计复杂的损失功能的其他步骤。实例量表中不可避免的变化可以导致自下而上的方法对超参数值特别敏感。为此，我们提出了一种动态的，无建议的，数据驱动的方法，该方法生成适当的卷积内核，以响应实例的性质。为了使内核有歧视性，我们通过收集具有相同语义类别并对几何质心的同质观点来探索较大的背景。然后，实例被几个简单的卷积层解码。由于稀疏卷积引入的接受场有限，因此还设计了一个小的轻质变压器来捕获点样品之间的远距离依赖性和高级相互作用。所提出的方法在scanetnetv2和s3dis上都取得了有希望的结果，并且该性能对于所选择的特定高参数值是可靠的。它还比当前的最新面积提高了推理速度超过25％。代码可在以下网址找到：https：//git.io/dyco3d
Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions. The inevitable variation in the instance scales can lead bottom-up methods to become particularly sensitive to hyper-parameter values. To this end, we propose instead a dynamic, proposal-free, data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. To make the kernels discriminative, we explore a large context by gathering homogeneous points that share identical semantic categories and have close votes for the geometric centroids. Instances are then decoded by several simple convolutional layers. Due to the limited receptive field introduced by the sparse convolution, a small light-weight transformer is also devised to capture the long-range dependencies and high-level interactions among point samples. The proposed method achieves promising results on both ScanetNetV2 and S3DIS, and this performance is robust to the particular hyper-parameter values chosen. It also improves inference speed by more than 25% over the current state-of-the-art. Code is available at: https://git.io/DyCo3D
