CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation
This work addresses the problem of efficiently and accurately estimating motion in autonomous driving systems by improving fusion of 2D and 3D data, though it is incremental in advancing existing fusion techniques.
The paper tackles the joint estimation of optical flow and scene flow from synchronized 2D and 3D data by proposing CamLiFlow, a novel end-to-end framework with bidirectional camera-LiDAR fusion, which achieves state-of-the-art performance on the KITTI Scene Flow benchmark with 1/7 the parameters of previous methods.
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 "late-fusion" 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 complementarity. 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. Code is available at https://github.com/MCG-NJU/CamLiFlow.