Range Adaptation for 3D Object Detection in LiDAR

TL;DR

This paper introduces a novel cross-range adaptation framework for LiDAR-based 3D object detection, improving far-range detection performance without extra model parameters, and demonstrates its effectiveness across multiple detection networks and datasets.

Contribution

It is the first to study cross-range LiDAR adaptation for object detection, proposing a model-agnostic framework validated on multiple networks and datasets.

Findings

Consistent performance improvements on far-range objects.

Effective adaptation without adding auxiliary parameters.

Validated across three state-of-the-art detection networks.

Abstract

LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes in properties across different observation ranges. In this paper, we explore cross-range adaptation for 3D object detection using LiDAR, i.e., far-range observations are adapted to near-range. This way, far-range detection is optimized for similar performance to near-range one. We adopt a bird-eyes view (BEV) detection framework to perform the proposed model adaptation. Our model adaptation consists of an adversarial global adaptation, and a fine-grained local adaptation. The proposed cross range adaptation framework is validated on three state-of-the-art LiDAR based object detection networks, and we consistently observe performance improvement on the far-range objects, without adding any auxiliary parameters to the model. To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds. To demonstrate the generality of the proposed adaptation framework, experiments on more challenging cross-device adaptation are further conducted, and a new LiDAR dataset with high-quality annotated point clouds is released to promote future research.