论文标题
ICAPS：迭代类别级对象姿势和形状估计
iCaps: Iterative Category-level Object Pose and Shape Estimation
论文作者
论文摘要
本文提出了类别级别的6D对象姿势和形状估计方法ICAPS，它允许跟踪类别中未见对象的6D姿势并估算其3D形状。我们使用深度图像作为输入开发类别级自动编码器网络，其中自动编码器中的功能嵌入了类别中对象的姿势。自动编码器可在粒子滤清器框架中使用，以估算和跟踪类别中对象的6D姿势。通过基于签名的距离函数来利用隐式形状表示形式，我们构建了一个潜在网，以估计3D形状的潜在表示，鉴于对象的估计姿势。然后，估计的姿势和形状可用于以迭代方式相互更新。我们的类别级别6D对象的姿势和形状估计管道仅需要2D检测和分割才能初始化。我们在公开可用的数据集上评估我们的方法并证明其有效性。特别是，我们的方法在形状估计上的精度相当高。
This paper proposes a category-level 6D object pose and shape estimation approach iCaps, which allows tracking 6D poses of unseen objects in a category and estimating their 3D shapes. We develop a category-level auto-encoder network using depth images as input, where feature embeddings from the auto-encoder encode poses of objects in a category. The auto-encoder can be used in a particle filter framework to estimate and track 6D poses of objects in a category. By exploiting an implicit shape representation based on signed distance functions, we build a LatentNet to estimate a latent representation of the 3D shape given the estimated pose of an object. Then the estimated pose and shape can be used to update each other in an iterative way. Our category-level 6D object pose and shape estimation pipeline only requires 2D detection and segmentation for initialization. We evaluate our approach on a publicly available dataset and demonstrate its effectiveness. In particular, our method achieves comparably high accuracy on shape estimation.
