论文标题
神经BF：自上而下实例分割的神经双边滤波
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
论文作者
论文摘要
我们介绍了一种方法，例如针对3D点云的提案生成。现有技术通常会在单个进料前的步骤中直接回归提案，从而导致估计不准确。我们表明，这是一个关键的瓶颈，并提出了一种基于迭代双边滤波的方法。遵循双边滤波的精神，我们考虑了每个点的深度嵌入以及它们在3D空间中的位置。我们通过合成实验显示，在为给定的兴趣点生成实例提案时，我们的方法会带来巨大的改进。我们进一步验证了我们的扫描仪基准的方法，从而在自上而下的方法的子类别中实现了最佳实例分割性能。
We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inaccurate estimation. We show that this serves as a critical bottleneck, and propose a method based on iterative bilateral filtering with learned kernels. Following the spirit of bilateral filtering, we consider both the deep feature embeddings of each point, as well as their locations in the 3D space. We show via synthetic experiments that our method brings drastic improvements when generating instance proposals for a given point of interest. We further validate our method on the challenging ScanNet benchmark, achieving the best instance segmentation performance amongst the sub-category of top-down methods.
