Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation
Scene flow estimation, which extracts point-wise motion between scenes, is becoming a crucial task in many computer vision tasks. However, all of the existing estimation methods utilize only the unidirectional features, restricting the accuracy and generality. This paper presents a novel scene flow estimation architecture using bidirectional flow embedding layers. The proposed bidirectional layer learns features along both forward and backward directions, enhancing the estimation performance. In addition, hierarchical feature extraction and warping improve the performance and reduce computational overhead. Experimental results show that the proposed architecture achieved a new state-of-the-art record by outperforming other approaches with large margin in both FlyingThings3D and KITTI benchmarks. Codes are available at https://github.com/cwc1260/BiFlow.
Code (1)
Tasks
Scene Flow EstimationSimilar Papers 제목 키워드 기반
PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds
Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not re…
Motion EstimationScene Flow EstimationSelf-Driving CarsTranslationMulti-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow Estimation
Scene flow estimation provides the fundamental motion perception of a dynamic scene, which is of practical importance in many computer vision applications. In this paper, we propose a novel multi-scale bidirectional …
Scene Flow EstimationSelf-Supervised 3D Scene Flow Estimation Guided by Superpoints
3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of l…
Scene Flow EstimationLearning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
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 st…
Optical Flow EstimationScene Flow EstimationScene Flow Estimation on KITTI 2015 Scene Flow TestRaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds
Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar…
Scene Flow EstimationPoint Clouds