Applied and Computational Mathematics (ACM)

ICCV2025 Paper Acceptance

26.06.2025|16:42 Uhr

Our work "TARS: Traffic-Aware Radar Scene Flow Estimation" by Jialong Wu , Marco Braun, Dominic Spata and Matthias Rottmann (Aptiv, Bergische Universität Wuppertal) has been accepted for publication at ICCV2025.

Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at instance level, assuming objects are rigid bodies. However, these instance-level methods are not suitable for sparse radar point clouds. TARS hierarchically models Radar scene flow and utilizes the motion rigidity rather at traffic flow level.

The preprint can be found here: https://arxiv.org/pdf/2503.10210

Congrats Jialong Wu, what an achievement!