解决合成数据到真实场景的追踪差距，提升仓库多视角多人追踪精度。
Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking
- 分三步修复合成到真实的数据鸿沟：校准、形状先验和目标数量假设。
- 在AI City Challenge 2026上实现52.0118的3D HOTA，无需重训练特征提取器。
- 适合关注多摄像头真实场景追踪的工业应用与算法研究者。
用于仓库场景的多摄像机3D感知系统主要在合成数据上训练，并在真实环境中评估。由此产生的合成到真实之间的差距，会破坏地平面定位和跨摄像机身份关联，通常被当作单一领域自适应模块需解决的问题；我们提出相反观点：该差距在三个可分离的环节中引入：相机标定、物体形状先验以及目标数量已知的假设，每个环节都应有对应的局部解决方案。我们的在线系统Syn2RealTrack采用此分解策略：仅从图像恢复镜头畸变，无需标定信息；通过可见性加权的部件级描述符融合多视角检测，对遮挡部分不猜测而是放弃；人体高度由标定直接闭式计算，而非复制合成先验；将封闭世界基数先验与因果滤波器结合，消除先验制造的虚假框。因此系统通过重新分配几何与外观的信任来实现自适应，无需重训练特征提取器。在AI City Challenge 2026 Track~1评测服务器上，达到52.0118的3D高阶追踪准确率（HOTA）。代码将于https://github.com/SKKUAutoLab/aic26_mc3dp发布。
原文摘要 · Abstract (English)
Multi-camera 3D perception systems for warehouse scenes are trained largely on synthetic data and evaluated on physically captured environments. The resulting synthetic-to-real gap, which corrupts ground-plane localization and cross-camera identity association, is usually treated as one deficiency for a single domain-adaptation module to absorb; we argue instead that it enters the pipeline at three separable points: the camera calibration, the object shape prior, and the assumption that the object census is known, each admitting a different local remedy. Our online pipeline, Syn2RealTrack, follows this decomposition: lens distortion is recovered from images alone under a calibration that provides none, detections are fused across views by a visibility-weighted part-based descriptor that abstains on occluded parts rather than guessing, person height is measured in closed form from calibration instead of copied from a synthetic prior, and a closed-world cardinality prior is paired with a causal filter that removes the phantom boxes the prior manufactures. The system therefore adapts by reallocating trust between geometry and appearance without retraining a feature extractor. On the AI City Challenge 2026 Track~1 evaluation server it reaches a 3D Higher Order Tracking Accuracy (HOTA) of 52.0118%. The code will be released at https://github.com/SKKUAutoLab/aic26_mc3dp
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。