In this work, we tackle the problem of category-level online pose tracking of objects from point cloud sequences. For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalent to a 3D amodal bounding box representation with free 6D pose. Given the depth point cloud at the current frame and the estimated pose from the last frame, our novel end-to-end pipeline learns to accurately update the pose. Our pipeline is composed of three modules: 1) a pose canonicalization module that normalizes the pose of the input depth point cloud; 2) RotationNet, a module that directly regresses small interframe delta rotations; and 3) CoordinateNet, a module that predicts the normalized coordinates and segmentation, enabling analytical computation of the 3D size and translation. Leveraging the small pose regime in the pose-canonicalized point clouds, our method integrates the best of both worlds by combining dense coordinate prediction and direct rotation regression, thus yielding an end-to-end differentiable pipeline optimized for 9DoF pose accuracy (without using non-differentiable RANSAC). Our extensive experiments demonstrate that our method achieves new state-of-the-art performance on category-level rigid object pose (NOCS-REAL275) and articulated object pose benchmarks (SAPIEN, BMVC) at the fastest FPS ~12.
翻译:在这项工作中,我们解决了从点云序列对物体进行在线分类层图像跟踪的问题。我们首次提出一个统一框架,可以处理9DoF对新式僵硬物体情况进行跟踪,也可以对已知类别中的直径物体进行每个部分的跟踪。9DoF对已知类别中由6D 表面和3D大小组成的9DF构成,相当于一个3D调式捆绑框表示,具有自由 6D 表面。鉴于当前框架的深度点云和最后一个框架的估计构成,我们新的端到端管道学会准确更新表面。我们的管道由三个模块组成:1)一个使输入深度云云层的构成正常化的布局软化气态物体模块;2) RotationNet,一个直接反向小型框架三角旋转的模块;3)ContalNet,一个预测正常坐标和分解的模块,能够对3D大小和翻译进行分析计算。在组合扫描点云中,我们的方法结合了两个目标的精度。我们的方法是两个目标的精度,将精度对输入精度的硬度 AL AL AL-RA 级的精确度的精确度预测和直接旋转,从而显示我们不具有最精确的RA的精确的BA的精确度的精确度,从而显示我们的精确度的精确度。