Scene flow estimation, which extracts point-wise motion between scenes, is
becoming a crucial task in many computer vision tasks. However, all of the
existing estimation methods utilize only the unidirectional features,
restricting the accuracy and generality. This paper presents a novel scene flow
estimation architecture using bidirectional flow embedding layers. The proposed
bidirectional layer learns features along both forward and backward directions,
enhancing the estimation performance. In addition, hierarchical feature
extraction and warping improve the performance and reduce computational
overhead. Experimental results show that the proposed architecture achieved a
new state-of-the-art record by outperforming other approaches with large margin
in both FlyingThings3D and KITTI benchmarks. Codes are available at
this https URL.

本文提出了使用双向流嵌入层的新型场景流估计体系结构，它学习了前向和后向方向的特征，增强了估算性能。实验结果表明，在 FlyingThings3D 和 KITTI 基准测试中，该体系结构表现非常优异，与其他方法相比具有明显的优势，并且通过代码已经得到验证。

Bi-PointFlowNet: 基于点云双向学习的场景流估计

Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation

This paper presents SO-Net, a permutation invariant architecture for deep
learning with orderless point clouds. The SO-Net models the spatial
distribution of point cloud by building a Self-Organizing Map (SOM). Based on
the SOM, SO-Net performs hierarchical feature extraction on individual points
and SOM nodes, and ultimately represents the input point cloud by a single
feature vector. The receptive field of the network can be systematically
adjusted by conducting point-to-node k nearest neighbor search. In recognition
tasks such as point cloud reconstruction, classification, object part
segmentation and shape retrieval, our proposed network demonstrates performance
that is similar with or better than state-of-the-art approaches. In addition,
the training speed is significantly faster than existing point cloud
recognition networks because of the parallelizability and simplicity of the
proposed architecture. Our code is available at the project website.
this https URL

本文介绍了 SO-Net，它是一种适用于无序点云的置换不变性架构，通过建立自组织映射（SOM）建模点云的空间分布，通过对点和 SOM 节点进行分层特征提取，最终将输入点云表示为单个特征向量。网络的感受野可以通过点到节点 k 近邻搜索进行系统调整， 在点云重建、分类、对象部分分割和形状检索等识别任务中，我们提出的网络表现出与最先进的方法相似或更好的性能。此外，由于所提出的架构的可并行性和简单性，训练速度显著快于现有点云识别网络。