Detecting objects in 3D space using multiple cameras, known as Multi-Camera 3D Object Detection (MC3D-Det), has gained prominence with the advent of bird's-eye view (BEV) approaches. However, these methods often struggle when faced with unfamiliar testing environments due to the lack of diverse training data encompassing various viewpoints and environments. To address this, we propose a novel method that aligns 3D detection with 2D camera plane results, ensuring consistent and accurate detections. Our framework, anchored in perspective debiasing, helps the learning of features resilient to domain shifts. In our approach, we render diverse view maps from BEV features and rectify the perspective bias of these maps, leveraging implicit foreground volumes to bridge the camera and BEV planes. This two-step process promotes the learning of perspective- and context-independent features, crucial for accurate object detection across varying viewpoints, camera parameters and environment conditions. Notably, our model-agnostic approach preserves the original network structure without incurring additional inference costs, facilitating seamless integration across various models and simplifying deployment. Furthermore, we also show our approach achieves satisfactory results in real data when trained only with virtual datasets, eliminating the need for real scene annotations. Experimental results on both Domain Generalization (DG) and Unsupervised Domain Adaptation (UDA) clearly demonstrate its effectiveness. Our code will be released.

翻译：利用多个相机在三维空间中进行目标检测（即多相机三维目标检测，MC3D-Det）随着鸟瞰图（BEV）方法的出现而日益受到重视。然而，由于缺乏涵盖各种视角和环境的多样化训练数据，这些方法在面对陌生测试环境时常常表现不佳。为此，我们提出了一种新颖方法，将三维检测与二维相机平面结果对齐，从而确保检测的一致性和准确性。我们的框架以视角去偏为核心，有助于学习对领域偏移具有鲁棒性的特征。在该方法中，我们从BEV特征渲染多样化的视角图，并利用隐式前景体素桥接相机平面与BEV平面，纠正这些视角图存在的视角偏差。这一两步过程促进了与视角和上下文无关特征的学习，对于在不同视角、相机参数和环境条件下实现准确的目标检测至关重要。值得注意的是，这种模型无关的方法保留了原始网络结构，且不增加额外推理成本，从而便于在不同模型间无缝集成并简化部署。此外，我们展示该方法在仅使用虚拟数据集训练时，也能在真实数据上取得满意结果，从而无需真实场景标注。在领域泛化（DG）和无监督领域自适应（UDA）上的实验结果明确证明了其有效性。我们的代码将开源。