arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.01129cs.CV
收藏

RMS-FlowNet++:面向大规模点云的高效且鲁棒的多尺度场景流估计

RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds

German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)

Ramy Battrawy, René Schuster, Didier Stricker

AI总结:

RMS-FlowNet++提出一种基于随机采样和流嵌入块的高效多尺度场景流估计架构,在保持高精度的同时显著降低内存需求,并可一次处理超过250K点的稠密点云。

摘要:

所提出的 RMS-FlowNet++ 是一种新颖的端到端基于学习的架构,用于在高密度点云上进行准确且高效的场景流估计。对于分层场景流估计,现有方法依赖昂贵的 Farthest-Point-Sampling(FPS)对场景进行采样,必须在连续帧之间寻找大量对应集合,并且/或者必须在完整输入分辨率下搜索对应关系。虽然这可以提高准确性,但会降低这些方法的整体效率,并由于内存需求限制其处理大量点的能力。与这些方法不同,我们的架构基于一种用于多尺度场景流分层预测的高效设计。为此,我们开发了一种特殊的流嵌入块,与当前方法相比具有两个优势:第一,使用更小的对应集合;第二,可以使用 Random-Sampling(RS)。此外,我们的架构不需要在完整输入分辨率下搜索对应关系。在表现出高准确性的同时,我们的 RMS-FlowNet++ 提供了比最先进方法更快的预测速度,避免了高内存需求,并能在超过 250K 点的稠密点云上一次完成高效的场景流估计。我们的综合实验在已建立的 FlyingThings3D 数据集上验证了 RMS-FlowNet++ 在不同点云密度下的准确性,并验证了我们的设计选择。此外,我们证明了我们的模型具有在不进行微调的情况下泛化到 KITTI 数据集真实世界场景的竞争能力。

英文摘要:

The proposed RMS-FlowNet++ is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation that can operate on high-density point clouds. For hierarchical scene f low estimation, existing methods rely on expensive Farthest-Point-Sampling (FPS) to sample the scenes, must find large correspondence sets across the consecutive frames and/or must search for correspondences at a full input resolution. While this can improve the accuracy, it reduces the overall efficiency of these methods and limits their ability to handle large numbers of points due to memory requirements. In contrast to these methods, our architecture is based on an efficient design for hierarchical prediction of multi-scale scene flow. To this end, we develop a special flow embedding block that has two advantages over the current methods: First, a smaller correspondence set is used, and second, the use of Random-Sampling (RS) is possible. In addition, our architecture does not need to search for correspondences at a full input resolution. Exhibiting high accuracy, our RMS-FlowNet++ provides a faster prediction than state-of-the-art methods, avoids high memory requirements and enables efficient scene flow on dense point clouds of more than 250K points at once. Our comprehensive experiments verify the accuracy of RMS FlowNet++ on the established FlyingThings3D data set with different point cloud densities and validate our design choices. Furthermore, we demonstrate that our model has a competitive ability to generalize to the real-world scenes of the KITTI data set without fine-tuning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑