Control Your Queries: Heterogeneous Query Interaction for Camera-Radar Fusion
Jialong Wu1,3 • Yihan Wang2, 3 • Matthias Rottmann1
1 Institute of Computer Science, Osnabrück University, Osnabrück, Germany
2 Department of Mathematics, University of Wuppertal, Wuppertal, Germany
3 Aptiv Services Deutschland GmbH
Abstract
In autonomous driving, camera-radar fusion offers complementary sensing and low deployment cost. Existing methods perform fusion through input mixing, feature map mixing, or query-based feature sampling. We propose a new fusion paradigm, termed heterogeneous query interaction, and present ConFusion, a camera-radar 3D object detector. ConFusion combines image queries, radar queries, and learnable world queries distributed in 3D space to improve query initialization and object coverage. To encourage cross-type interaction among heterogeneous queries, we introduce heterogeneous query mixing (QMix), which performs dedicated cross-type attention after feature sampling to consolidate complementary object evidence. We further propose interactive query swap sampling (QSwap), which improves feature sampling by allowing related queries to exchange informative feature tokens under attention and geometric constraints. Experiments on the nuScenes dataset show that ConFusion achieves state-of-the-art performance, reaching 59.1 mAP and 65.6 NDS on the validation set, and 61.6 mAP and 67.9 NDS on the test set.
Resources & Links
Acknowledgments
J.W. and M.R. acknowledge support by the German Federal Ministry of Education and Research within the junior research group project “UnrEAL” (grant no. 01IS22069).
Citation
@misc{wu2026controlqueriesheterogeneousquery,
title={Control Your Queries: Heterogeneous Query Interaction for Camera-Radar Fusion},
author={Jialong Wu and Yihan Wang and Matthias Rottmann},
year={2026},
eprint={2604.25574},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2604.25574},
}
Contact
Have questions or want to collaborate? Reach out:
- Email: jialwu@uni-osnabrueck.de