Hybrid Bayesian Eigenobjects: Combining Linear Subspace and Deep Network Methods for 3D Robot Vision
This addresses the challenge of efficient and accurate 3D object understanding for robots, with incremental improvements in combining existing methods.
The paper tackled the problem of joint pose, class, and 3D geometry estimation for novel objects from a single viewpoint in robot vision, resulting in dramatically improved performance and several orders of magnitude faster runtime compared to prior work.
We introduce Hybrid Bayesian Eigenobjects (HBEOs), a novel representation for 3D objects designed to allow a robot to jointly estimate the pose, class, and full 3D geometry of a novel object observed from a single viewpoint in a single practical framework. By combining both linear subspace methods and deep convolutional prediction, HBEOs efficiently learn nonlinear object representations without directly regressing into high-dimensional space. HBEOs also remove the onerous and generally impractical necessity of input data voxelization prior to inference. We experimentally evaluate the suitability of HBEOs to the challenging task of joint pose, class, and shape inference on novel objects and show that, compared to preceding work, HBEOs offer dramatically improved performance in all three tasks along with several orders of magnitude faster runtime performance.