Uncertainty-aware Self-supervised 3D Data Association

TL;DR

This paper introduces a self-supervised approach for 3D data association in object tracking, leveraging unlabeled data and uncertainty estimation to improve robustness and accuracy without requiring manual annotations.

Contribution

It proposes a novel uncertainty-aware self-supervised learning method for 3D data association, reducing reliance on labeled datasets and enhancing tracking robustness.

Findings

Effective 3D tracking with self-supervised embeddings

Uncertainty modeling improves data association accuracy

Method outperforms traditional supervised approaches

Abstract

3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datasets by self-supervised metric learning of 3D object trackers, with a focus on data association. Large scale annotations for unlabeled data are cheaply obtained by automatic object detection and association across frames. We show how these self-supervised annotations can be used in a principled manner to learn point-cloud embeddings that are effective for 3D tracking. We estimate and incorporate uncertainty in self-supervised tracking to learn more robust embeddings, without needing any labeled data. We design embeddings to differentiate objects across frames, and learn them using uncertainty-aware self-supervised training. Finally, we demonstrate their ability to perform accurate data association across frames, towards effective and accurate 3D tracking. Project videos and code are at https://jianrenw.github.io/Self-Supervised-3D-Data-Association.