English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Scene flow estimation, which predicts the 3D motion of scene points frompoint clouds, is a core task in autonomous driving and many other 3D visionapplications. Existing methods either suffer from structure distortion due toignorance of rigid motion consistency or require explicit pose estimation and3D object segmentation. Errors of estimated poses and segmented objects wouldyield inaccurate rigidity constraints and in turn mislead scene flowestimation. In this paper, we propose a novel weight-sharing aggregation (WSA)method for feature and scene flow up-sampling. WSA does not rely on estimatedposes and segmented objects, and can implicitly enforce rigidity constraints toavoid structure distortion in scene flow estimation. To further exploitgeometric information and preserve local structure, we design a deformationdegree module aim to keep the local region invariance. We modify thePointPWC-Net and integrate the proposed WSA and deformation degree module intothe enhanced PointPWC-Net to derive an end-to-end scene flow estimationnetwork, called WSAFlowNet. Extensive experimental results on theFlyingThings3D and KITTI datasets demonstrate that our WSAFlowNet achieves thestate-of-the-art performance and outperforms previous methods by a largemargin. We will release the source code athttps://github.com/wangyunlhr/WSAFlowNet.git.

Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds