HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds
复制标题
DOI：
10.1109/cvpr.2019.00337
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Xiuye Gu;Yijie Wang;Chongruo Wu;Yong Jae Lee;Panqu Wang
中科院分区：
文献类型：
--
作者：
Xiuye Gu;Yijie Wang;Chongruo Wu;Yong Jae Lee;Panqu Wang
我们提出了一种新的深度神经网络架构，用于直接在大规模3D点云上进行端到端场景流估计。受双边卷积层（BCL）的启发，我们提出了新的DownBCL，UpBCL和CorrBCL操作，从非结构化点云恢复结构信息，并融合来自两个连续点云的信息。操作离散和稀疏的permutohedral格点，我们的架构设计是节俭的计算成本。我们的模型可以有效地处理一对点云帧，每帧最多86K个点。我们的方法在FlyingThings3D和KITTI Scene Flow 2015数据集上实现了最先进的性能。此外，在合成数据上训练，我们的方法在真实世界的数据和不同的点密度上显示出很强的泛化能力，而无需微调。
We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds. Inspired by Bilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, and CorrBCL operations that restore structural information from unstructured point clouds, and fuse information from two consecutive point clouds. Operating on discrete and sparse permutohedral lattice points, our architectural design is parsimonious in computational cost. Our model can efficiently process a pair of point cloud frames at once with a maximum of 86K points per frame. Our approach achieves state-of-the-art performance on the FlyingThings3D and KITTI Scene Flow 2015 datasets. Moreover, trained on synthetic data, our approach shows great generalization ability on real-world data and on different point densities without fine-tuning.