Point2Pose：基于2D点跟踪器的遮挡恢复多未知物体6D姿态跟踪与3D重建
Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers
AI总结：
Point2Pose利用2D点跟踪器实现多未知物体的6D姿态跟踪与3D重建，在完全遮挡后能快速恢复，无需CAD模型或类别先验。
摘要：
我们提出了Point2Pose，一种无需模型的因果6D姿态跟踪方法，从单目RGB-D视频中跟踪多个刚体物体。仅需稀疏图像点初始化，无需物体CAD模型或类别先验。Point2Pose利用2D点跟踪器获得长距离对应关系，实现完全遮挡后的即时恢复。同时系统逐步构建在线截断签名距离函数（TSDF）表示。我们还引入了一个包含仿真和真实世界序列的多物体跟踪数据集，包含运动捕捉地面真实数据用于评估。实验表明，Point2Pose在严重遮挡基准上性能与最先进方法相当，同时支持多物体跟踪和完全遮挡恢复，这是之前无模型跟踪方法所不具备的能力。
英文摘要：
We present Point2Pose, a model-free method for causal 6D pose tracking of multiple rigid objects from monocular RGB-D video. Initialized only from sparse image points on the objects, our approach tracks multiple unseen objects without requiring object CAD models or category priors. Point2Pose leverages a 2D point tracker to obtain long-range correspondences, enabling instant recovery after complete occlusion. Simultaneously, the system incrementally reconstructs an online Truncated Signed Distance Function (TSDF) representation of the tracked targets. Alongside the method, we introduce a new multi-object tracking dataset comprising both simulation and real-world sequences, with motion-capture ground truth for evaluation. Experiments show that Point2Pose trades some single-object pose accuracy for broader model-free tracking capabilities, including multi-object tracking and recovery from complete occlusion. Project page: https://point2pose.github.io/.
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。
