Fully Convolutional Geometric Features for Category-level Object Alignment

TL;DR

This paper introduces a fully convolutional geometric feature method for category-level object alignment, enabling robust pose registration of different object instances within the same category, crucial for online object mapping.

Contribution

It proposes a novel approach that transforms object instances to a canonical frame and uses metric learning to generate matching features for accurate registration.

Findings

Robust features for category-level registration

Accurate alignment of objects with different shapes

Effective on both synthetic and real-world data

Abstract

This paper focuses on pose registration of different object instances from the same category. This is required in online object mapping because object instances detected at test time usually differ from the training instances. Our approach transforms instances of the same category to a normalized canonical coordinate frame and uses metric learning to train fully convolutional geometric features. The resulting model is able to generate pairs of matching points between the instances, allowing category-level registration. Evaluation on both synthetic and real-world data shows that our method provides robust features, leading to accurate alignment of instances with different shapes.