提出多相机布局基准，研究自动驾驶感知在不同摄像头布置下的泛化能力。
Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics
- 构建14种系统化设计的摄像头布局，在相同场景下测试感知模型表现。
- 发现摄像头几何布局差异导致性能显著波动，最大降幅超20%。
- 提出两种度量指标，可预测不同布局间迁移难易程度，适合车载系统研发者。
基于摄像头的自动驾驶感知系统通常在固定传感器布局下开发与评估，而真实车辆车队中摄像头的位置、朝向、视场角和数量存在显著差异。这种差异引入了仅几何观测过程变化的跨布局领域差距。为在受控条件下研究该影响，我们提出Plentiful CARLA Camera Rigs基准，可在14种系统设计的摄像头布局下渲染相同驾驶场景。该设置使跨布局泛化分析成为可能，且不受场景内容或外观干扰。利用该基准，我们分析了典型多视角感知架构的跨布局迁移行为，观察到由几何布局变化引发的显著性能波动。为进一步支持结构化分析，我们引入两个基于标定信息的描述符：Rig Variance（衡量布局内部多样性）与Rig Contrastive Distance（测量布局间几何差异）。实验表明，几何布局差异与相对跨布局性能变化高度相关，且Rig Contrastive Distance能有效作为布局间迁移难度排序的可靠代理。
原文摘要 · Abstract (English)
Camera-based perception systems for autonomous driving are typically developed and evaluated using fixed sensor rigs, while real-world vehicle fleets exhibit substantial variation in camera placement, orientation, field of view, and camera count. This mismatch introduces a cross-rig domain gap in which only the geometric observation process changes. To study this effect under controlled conditions, we introduce Plentiful CARLA Camera Rigs, a benchmark that renders identical driving scenes under 14 systematically designed camera rigs. This setup enables direct analysis of cross-rig generalization without confounding changes in scene content or appearance. Using the benchmark, we analyze cross-rig transfer behavior of representative multi-view perception architectures and observe substantial performance shifts induced by geometric rig variation. To facilitate structured analysis, we further introduce two calibration-based descriptors derived from rig metadata: Rig Variance, capturing internal rig diversity, and Rig Contrastive Distance, measuring geometric discrepancy between rigs. Our experiments show that geometric rig differences strongly correlate with relative cross-rig performance shifts and that Rig Contrastive Distance provides a reliable proxy for ranking transfer difficulty between sensor rigs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。