论文标题
朝着自我监督的类别级对象姿势和尺寸估计
Towards Self-Supervised Category-Level Object Pose and Size Estimation
论文作者
论文摘要
在这项工作中，我们从单个深度图像中解决了类别级对象姿势和大小估计的具有挑战性的问题。尽管以前的全面监督作品表现出了令人鼓舞的表现，但收集地面姿势标签通常是耗时且劳动力密集的。取而代之的是，我们提出了一种无标签的方法，该方法学会在自学措施方式下使用类别模板网格和观察到的对象点云之间的几何一致性。具体而言，我们的方法由三个关键组成部分组成：可区分形状变形，注册和渲染。特别是，将形状的变形和注册应用于模板网格，以消除形状，姿势和尺度的差异。然后，部署一个可区分的渲染器，以从渲染深度和观察到的自我掩盖的场景中抬高点云之间的几何一致性。我们在现实世界数据集上评估了我们的方法，并发现我们的方法的表现优于传统基线，而较大的利润率则与一些完全监督的方法竞争。
In this work, we tackle the challenging problem of category-level object pose and size estimation from a single depth image. Although previous fully-supervised works have demonstrated promising performance, collecting ground-truth pose labels is generally time-consuming and labor-intensive. Instead, we propose a label-free method that learns to enforce the geometric consistency between category template mesh and observed object point cloud under a self-supervision manner. Specifically, our method consists of three key components: differentiable shape deformation, registration, and rendering. In particular, shape deformation and registration are applied to the template mesh to eliminate the differences in shape, pose and scale. A differentiable renderer is then deployed to enforce geometric consistency between point clouds lifted from the rendered depth and the observed scene for self-supervision. We evaluate our approach on real-world datasets and find that our approach outperforms the simple traditional baseline by large margins while being competitive with some fully-supervised approaches.
