Category-Agnostic 6D Pose Estimation with Conditional Neural Processes. (arXiv:2206.07162v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07162

We present a novel meta-learning approach for 6D pose estimation on unknown
objects. In contrast to "instance-level" pose estimation methods, our algorithm
learns object representation in a category-agnostic way, which endows it with
strong generalization capabilities within and across object categories.
Specifically, we employ a conditional neural process-based meta-learning
approach to train an encoder to capture texture and geometry of an object in a
latent representation, based on very few RGB-D images and ground-truth
keypoints. The latent representation is then …

arxiv category- cv neural processes