Deep learning-based intelligent vehicle perception has been develo** prominently in
recent years to provide a reliable source for motion planning and decision making in …

Scene flow characterizes the 3D motion between two LiDAR scans captured by an
autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point …

Abstract 3D scene flow estimation aims to estimate point-wise motions between two
consecutive frames of point clouds. Superpoints, ie, points with similar geometric features …

A key challenge for autonomous vehicles is to navigate in unseen dynamic environments.
Separating moving objects from static ones is essential for navigation, pose estimation, and …

Recently, several frameworks for self-supervised learning of 3D scene flow on point clouds
have emerged. Scene flow inherently separates every scene into multiple moving agents …

Abstract Neural Scene Flow Prior (NSFP) is of significant interest to the vision community
due to its inherent robustness to out-of-distribution (OOD) effects and its ability to deal with …

Understanding the scene is key for autonomously navigating vehicles, and the ability to
segment the surroundings online into moving and non-moving objects is a central ingredient …

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-
modal learning. Our approach is motivated by the co-located sensing redundancy in modern …

Semantic scene interpretation is essential for autonomous systems to operate in complex
scenarios. While deep learning-based methods excel at this task, they rely on vast amounts …

Learning 3D scene flow from LiDAR point clouds presents significant difficulties including
poor generalization from synthetic datasets to real scenes scarcity of real-world 3D labels …