RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
This work addresses the challenge of scene flow estimation for large-scale point clouds, which is crucial for applications like autonomous driving and robotics, though it is incremental in improving efficiency over existing methods.
The paper tackles the problem of efficient and accurate scene flow estimation on high-density point clouds by proposing RMS-FlowNet++, which uses a novel flow embedding block with random sampling and smaller correspondence sets to reduce memory usage and improve speed. It achieves faster predictions than state-of-the-art methods while handling over 250K points and generalizes competitively to real-world datasets like KITTI without fine-tuning.
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.