Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
This addresses the problem of robust pose estimation for varied object instances in robotics and computer vision, representing an incremental improvement with a novel method.
The paper tackles intra-class shape variations for category-level 6D object pose and size estimation by learning a canonical shape space (CASS) using a VAE to generate 3D point clouds from RGBD images, achieving state-of-the-art performance.
We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category. In particular, CASS is modeled as the latent space of a deep generative model of canonical 3D shapes with normalized pose. We train a variational auto-encoder (VAE) for generating 3D point clouds in the canonical space from an RGBD image. The VAE is trained in a cross-category fashion, exploiting the publicly available large 3D shape repositories. Since the 3D point cloud is generated in normalized pose (with actual size), the encoder of the VAE learns view-factorized RGBD embedding. It maps an RGBD image in arbitrary view into a pose-independent 3D shape representation. Object pose is then estimated via contrasting it with a pose-dependent feature of the input RGBD extracted with a separate deep neural networks. We integrate the learning of CASS and pose and size estimation into an end-to-end trainable network, achieving the state-of-the-art performance.