In this article, we investigate self-supervised 3D scene flow estimation and class-agnostic motion prediction on point clouds. A realistic scene can be well modeled as a collection of rigidly moving parts, therefore its scene flow can be represented as a combination of the rigid motion of these individual parts. Building upon this observation, we propose to generate pseudo scene flow labels for self-supervised learning through piecewise rigid motion estimation, in which the source point cloud is decomposed into local regions and each region is treated as rigid. By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to generate its pseudo flow labels. To mitigate the impact of potential outliers on label generation, when solving the rigid registration for each region, we alternately perform three steps: establishing point correspondences, measuring the confidence for the correspondences, and updating the rigid transformation based on the correspondences and their confidence. As a result, confident correspondences will dominate label generation and a validity mask will be derived for the generated pseudo labels. By using the pseudo labels together with their validity mask for supervision, models can be trained in a self-supervised manner. Extensive experiments on FlyingThings3D and KITTI datasets demonstrate that our method achieves new state-of-the-art performance in self-supervised scene flow learning, without any ground truth scene flow for supervision, even performing better than some supervised counterparts. Additionally, our method is further extended to class-agnostic motion prediction and significantly outperforms previous state-of-the-art self-supervised methods on nuScenes dataset.

翻译：本文研究了点云上的自监督三维场景流估计及类别无关的运动预测。真实场景可被良好地建模为多个刚性运动部件的集合，因此其场景流可表示为这些独立部件刚体运动的组合。基于这一观察，我们提出通过分段刚体运动估计来生成用于自监督学习的伪场景流标签，其中源点云被分解为局部区域，每个区域被视为刚体。通过将每个区域与目标点云中可能的对应区域进行刚体对齐，我们获得区域特定的刚体变换以生成其伪流标签。为减轻潜在异常值对标签生成的影响，在求解每个区域的刚体配准时，我们交替执行三个步骤：建立点对应关系、测量对应关系的置信度、以及基于对应关系及其置信度更新刚体变换。由此，高置信度对应关系将主导标签生成，并为生成的伪标签导出有效性掩码。通过将伪标签及其有效性掩码用于监督，模型可以以自监督方式进行训练。在FlyingThings3D和KITTI数据集上的大量实验表明，我们的方法在自监督场景流学习中达到了新的最优性能，无需任何真实场景流作为监督，甚至优于某些有监督方法。此外，我们将方法进一步扩展到类别无关的运动预测中，在nuScenes数据集上显著超越了先前最优的自监督方法。