Robust Collaborative 3D Object Detection in Presence of Pose Errors

TL;DR

CoAlign is a robust hybrid framework for collaborative 3D object detection that effectively mitigates pose estimation errors without requiring ground-truth pose supervision, improving detection accuracy in practical scenarios.

Contribution

The paper introduces CoAlign, a novel agent-object pose graph and multi-scale data fusion approach that enhances robustness to pose errors in collaborative 3D detection.

Findings

Significantly reduces localization error under pose inaccuracies

Achieves state-of-the-art detection performance with pose errors

Does not require ground-truth pose supervision during training

Abstract

Collaborative 3D object detection exploits information exchange among multiple agents to enhance accuracy of object detection in presence of sensor impairments such as occlusion. However, in practice, pose estimation errors due to imperfect localization would cause spatial message misalignment and significantly reduce the performance of collaboration. To alleviate adverse impacts of pose errors, we propose CoAlign, a novel hybrid collaboration framework that is robust to unknown pose errors. The proposed solution relies on a novel agent-object pose graph modeling to enhance pose consistency among collaborating agents. Furthermore, we adopt a multi-scale data fusion strategy to aggregate intermediate features at multiple spatial resolutions. Comparing with previous works, which require ground-truth pose for training supervision, our proposed CoAlign is more practical since it doesn't require any ground-truth pose supervision in the training and makes no specific assumptions on pose errors. Extensive evaluation of the proposed method is carried out on multiple datasets, certifying that CoAlign significantly reduce relative localization error and achieving the state of art detection performance when pose errors exist. Code are made available for the use of the research community at https://github.com/yifanlu0227/CoAlign.