无需标定和标注，实现多摄像头多目标追踪的自监督特征分离。
CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking
- 通过单视角蒸馏与跨视角重建，分离通用视图与特定视图特征。
- 在MMP-MvMHAT上提升3%总体准确率，平均F1分数提高7.5%。
- 适用于复杂动态场景，对不同摄像头配置适应性强。
多摄像头多目标追踪（MCMOT）在保持跨视角物体身份一致性方面面临挑战，尤其当需要精确标定和大量人工标注时。本文提出CalibFree，一种无需任何标定或人工标注的自监督表示学习框架。通过单视角蒸馏和跨视角重建，促进视图无关与视图特定特征的分离，使方法在复杂动态场景中具备低开销适应能力。在MMP-MvMHAT数据集上的实验表明，整体准确率提升3%，平均F1分数提高7.5%，优于当前最优方法。在更具多样性的MvMHAT数据集上，该方法展现出更强的长时间追踪能力和跨视角性能，证明其对多种摄像头配置的良好适应性。代码将在录用后公开。
原文摘要 · Abstract (English)
Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this paper, we present CalibFree, a self-supervised representation learning framework that does not need any calibration or manual labeling for the MCMOT task. By promoting feature separation between view-agnostic and view-specific representations through single-view distillation and cross-view reconstruction, our method adapts to complex, dynamic scenarios with minimal overhead. Experiments on the MMP-MvMHAT dataset show a 3% improvement in overall accuracy and a 7.5% increase in the average F1 score over state-of-the-art approaches, confirming the effectiveness of our calibration-free design. Moreover, on the more diverse MvMHAT dataset, our approach demonstrates superior over-time tracking and strong cross-view performance, highlighting its adaptability to a wide range of camera configurations. Code will be publicly available upon acceptance.
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。