The wide deployment of multi-modal sensors in various areas generates vast amounts of
data with characteristics of high volume, wide variety, and high integrity. However, traditional …

Before the deep learning revolution, many perception algorithms were based on runtime
optimization in conjunction with a strong prior/regularization penalty. A prime example of this …

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 …

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 …

Abstract 3D scene flow estimation from point clouds is a low-level 3D motion perception task
in computer vision. Flow embedding is a commonly used technique in 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 …

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 …

In this work, we focus on scene flow learning on point clouds in a self-supervised manner. A
real-world scene can be well modeled as a collection of rigidly moving parts, therefore its …

Scene flow estimation is a long-standing problem in computer vision, where the goal is to
find the 3D motion of a scene from its consecutive observations. Recently, there have been …

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike
all existing methods which usually require a large amount of human annotations for full …