See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation

Abstract

Sampling discrepancies between different manufacturers and models of lidar sensors result in inconsistent representations of objects. This leads to performance degradation when 3D detectors trained for one lidar are tested on other types of lidars. Remarkable progress in lidar manufacturing has brought about advances in mechanical, solid-state, and recently, adjustable scan pattern lidars. For the latter, existing works often require fine-tuning the model each time scan patterns are adjusted, which is infeasible. We explicitly deal with the sampling discrepancy by proposing a novel unsupervised multi-target domain adaptation framework, SEE, for transferring the performance of state-of-the-art 3D detectors across both fixed and flexible scan pattern lidars without requiring fine-tuning of models by end-users. Our approach interpolates the underlying geometry and normalizes the scan pattern of objects from different lidars before passing them to the detection network. We demonstrate the effectiveness of SEE on public datasets, achieving state-of-the-art results, and additionally provide quantitative results on a novel high-resolution lidar to prove the industry applications of our framework.

Published in RAL and presented in IROS 2022. Code is available at https://github.com/darrenjkt/SEE-MTDA

References in corpus (10)

• Learning Transferable Features with Deep Adaptation Networks
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Open3D: A Modern Library for 3D Data Processing
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• Correlation Alignment by Riemannian Metric for Domain Adaptation
• Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection

Cited by in corpus (4)

• Quantifying the LiDAR Sim-to-Real Domain Shift: A Detailed Investigation Using Object Detectors and Analyzing Point Clouds at Target-Level
• SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
• MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection
• DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoising