论文标题
分类6D对象姿势和尺寸估计的形状先验变形
Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation
论文作者
论文摘要
我们提出了一种新颖的学习方法，可以从RGB-D图像中恢复未见对象实例的6D姿势和大小。为了处理阶层内形状变化，我们提出了一个深层网络来通过明确对先验的分类形状进行明确对变形进行建模，以重建3D对象模型。此外，我们的网络渗透了对象实例的深度观察与重建的3D模型之间的密集对应关系，以共同估计6D对象的姿势和大小。我们设计了一个自动编码器，该自动编码器会训练对象模型的集合，并为每个类别的平均潜在嵌入方式计算出分类形状先验。对合成和现实世界数据集的广泛实验表明，我们的方法显着优于最新技术。我们的代码可在https://github.com/mentian/object-deformnet上找到。
We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. To handle the intra-class shape variation, we propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior. Additionally, our network infers the dense correspondences between the depth observation of the object instance and the reconstructed 3D model to jointly estimate the 6D object pose and size. We design an autoencoder that trains on a collection of object models and compute the mean latent embedding for each category to learn the categorical shape priors. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly outperforms the state of the art. Our code is available at https://github.com/mentian/object-deformnet.
