FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

TL;DR

FlowMamba introduces a global-aware scene flow estimation network that effectively propagates global motion patterns in point clouds, achieving millimeter-level accuracy and outperforming existing methods on standard datasets.

Contribution

The paper presents a novel Iterative Unit based on the State Space Model with a feature-induced ordering strategy, enhancing scene flow estimation in challenging regions.

Findings

Achieves 21.9% and 20.5% EPE3D reduction on FlyingThings3D and KITTI datasets.

First method to reach millimeter-level accuracy in scene flow prediction.

ISU module can be integrated into existing networks to improve accuracy.

Abstract

Scene flow methods based on deep learning have achieved impressive performance. However, current top-performing methods still struggle with ill-posed regions, such as extensive flat regions or occlusions, due to insufficient local evidence. In this paper, we propose a novel global-aware scene flow estimation network with global motion propagation, named FlowMamba. The core idea of FlowMamba is a novel Iterative Unit based on the State Space Model (ISU), which first propagates global motion patterns and then adaptively integrates the global motion information with previously hidden states. As the irregular nature of point clouds limits the performance of ISU in global motion propagation, we propose a feature-induced ordering strategy (FIO). The FIO leverages semantic-related and motion-related features to order points into a sequence characterized by spatial continuity. Extensive experiments demonstrate the effectiveness of FlowMamba, with 21.9\% and 20.5\% EPE3D reduction from the best published results on FlyingThings3D and KITTI datasets. Specifically, our FlowMamba is the first method to achieve millimeter-level prediction accuracy in FlyingThings3D and KITTI. Furthermore, the proposed ISU can be seamlessly embedded into existing iterative networks as a plug-and-play module, improving their estimation accuracy significantly.