HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding

TL;DR

HCRF-Flow introduces a novel scene flow estimation method from point clouds that incorporates high-order CRFs and position-aware flow embedding to enforce local rigidity and smoothness, achieving state-of-the-art results.

Contribution

The paper presents a high-order CRFs based relation module combined with position-aware flow embedding for improved scene flow estimation from point clouds.

Findings

Achieves state-of-the-art performance on FlyingThings3D and KITTI datasets.

Significantly outperforms previous methods in accuracy.

Effectively enforces local rigidity and smoothness constraints.

Abstract

Scene flow in 3D point clouds plays an important role in understanding dynamic environments. Although significant advances have been made by deep neural networks, the performance is far from satisfactory as only per-point translational motion is considered, neglecting the constraints of the rigid motion in local regions. To address the issue, we propose to introduce the motion consistency to force the smoothness among neighboring points. In addition, constraints on the rigidity of the local transformation are also added by sharing unique rigid motion parameters for all points within each local region. To this end, a high-order CRFs based relation module (Con-HCRFs) is deployed to explore both point-wise smoothness and region-wise rigidity. To empower the CRFs to have a discriminative unary term, we also introduce a position-aware flow estimation module to be incorporated into the Con-HCRFs. Comprehensive experiments on FlyingThings3D and KITTI show that our proposed framework (HCRF-Flow) achieves state-of-the-art performance and significantly outperforms previous approaches substantially.