Pose Induction for Novel Object Categories
This addresses pose estimation for novel object categories, enabling applications like shape model learning, but it appears incremental as it builds on existing methods for pose prediction.
The paper tackles the problem of predicting object pose for unannotated categories using a small seed set of annotated classes, achieving reliable pose estimates with a generalized classifier that improves with more instances.
We address the task of predicting pose for objects of unannotated object categories from a small seed set of annotated object classes. We present a generalized classifier that can reliably induce pose given a single instance of a novel category. In case of availability of a large collection of novel instances, our approach then jointly reasons over all instances to improve the initial estimates. We empirically validate the various components of our algorithm and quantitatively show that our method produces reliable pose estimates. We also show qualitative results on a diverse set of classes and further demonstrate the applicability of our system for learning shape models of novel object classes.