papers AI Learner
The Github is limit! Click to go to the new site.

Probabilistic Category-Level Pose Estimation via Segmentation and Predicted-Shape Priors

2019-05-28
Benjamin Burchfiel, George Konidaris

Abstract

We introduce a new method for category-level pose estimation which produces a distribution over predicted poses by integrating 3D shape estimates from a generative object model with segmentation information. Given an input depth-image of an object, our variable-time method uses a mixture density network architecture to produce a multi-modal distribution over 3DOF poses; this distribution is then combined with a prior probability encouraging silhouette agreement between the observed input and predicted object pose. Our approach significantly outperforms the current state-of-the-art in category-level 3DOF pose estimation—which outputs a point estimate and does not explicitly incorporate shape and segmentation information—as measured on the Pix3D and ShapeNet datasets.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.12079

PDF

http://arxiv.org/pdf/1905.12079


Similar Posts

Comments