Learned Fusion：采用免校准Transformer特征融合的3D目标检测
Learned Fusion: 3D Object Detection using Calibration-Free Transformer Feature Fusion
AI总结：
针对现有3D目标检测传感器融合高度依赖标定、难大规模部署的问题，提出首个免校准方法，用transformer跨传感器多抽象层级映射特征，BEV mAP较单模态提升14.1%，且对旋转平移变化鲁棒，为免校准融合研究提供新方向。
摘要：
当前基于传感器融合的3D目标检测前沿方法高度依赖标定质量，这在实验室外的大规模部署中难以维持。我们提出了首个面向3D目标检测的免校准方法，从而省去了复杂且成本高昂的标定流程。该方法利用transformer在多个抽象层级上映射不同传感器多视图间的特征。在大规模目标检测评估中，我们不仅证明该方法的BEV mAP比单模态方案高14.1%，还证实transformer确实学会了映射关系。通过证明传感器融合无需标定，我们希望推动其他研究者跟进免校准融合方向。此外，所得方法对旋转和平移变化具备强鲁棒性。
英文摘要：
The state of the art in 3D object detection using sensor fusion heavily relies on calibration quality, which is difficult to maintain in large scale deployment outside a lab environment. We present the first calibration-free approach for 3D object detection. Thus, eliminating the need for complex and costly calibration procedures. Our approach uses transformers to map the features between multiple views of different sensors at multiple abstraction levels. In an extensive evaluation for object detection, we not only show that our approach outperforms single modal setups by 14.1% in BEV mAP, but also that the transformer indeed learns mapping. By showing calibration is not necessary for sensor fusion, we hope to motivate other researchers following the direction of calibration-free fusion. Additionally, resulting approaches have a substantial resilience against rotation and translation changes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
