论文标题
Bi-Pointflownet：基于点云的场景流估计的双向学习
Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation
论文作者
论文摘要
场景流估计在场景之间提取点运动的场景估计正在成为许多计算机视觉任务的关键任务。但是，所有现有的估计方法仅利用单向特征，从而限制了准确性和通用性。本文使用双向流嵌入层提出了一种新颖的场景估计架构。所提出的双向层学习沿向前和向后方向的功能，从而提高估计性能。此外，分层特征提取和扭曲可改善性能并减少计算开销。实验结果表明，拟议的架构通过在FlyingThings3D和Kitti基准测试中优于其他方法，从而获得了新的最新记录。代码可在https://github.com/cwc1260/biflow上找到。
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 https://github.com/cwc1260/BiFlow.
