CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation

In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an early-fusion or latefusion manner. Such one-size-fits-all approaches suffer from a dilemma of failing to fully utilize the characteristic of each modality or to maximize the inter-modality complementarily. To address the problem, we propose a novel end-to-end framework, called CamLiFlow. It consists of 2D and 3D branches with multiple bidirectional connections between them in specific layers. Different from previous work, we apply a point-based 3D branch to better extract the geometric features and design a symmetric learnable operator to fuse dense image features and sparse point features. Experiments show that CamLiFlow achieves better performance with fewer parameters. Our method ranks 1st on the KITTI Scene Flow benchmark, outperforming the previous art with 1/7 parameters.

Automated summary

This paper studies the problem of estimating optical flow and scene flow from synchronized 2D and 3D data. A novel end-to-end framework, called CamLiFlow, is proposed to address this problem. It consists of 2D and 3D branches with bidirectional connections and applies a point-based 3D branch to extract geometric features. Experimental results show that CamLiFlow achieves better performance with fewer parameters and ranks 1st on the KITTI Scene Flow benchmark.