Learning Descriptors for Object Recognition and 3D Pose Estimation

TL;DR

This paper presents a neural network-based descriptor learning method that improves object recognition and 3D pose estimation by enabling efficient similarity measurement and handling large datasets with diverse poses.

Contribution

We introduce a CNN-based descriptor learning approach that captures object identity and pose, outperforming previous manifold-based methods in efficiency and accuracy.

Findings

Descriptors are well-separated for different objects.

Euclidean distance correlates with pose difference.

Outperforms state-of-the-art on RGB and RGB-D data.

Abstract

Detecting poorly textured objects and estimating their 3D pose reliably is still a very challenging problem. We introduce a simple but powerful approach to computing descriptors for object views that efficiently capture both the object identity and 3D pose. By contrast with previous manifold-based approaches, we can rely on the Euclidean distance to evaluate the similarity between descriptors, and therefore use scalable Nearest Neighbor search methods to efficiently handle a large number of objects under a large range of poses. To achieve this, we train a Convolutional Neural Network to compute these descriptors by enforcing simple similarity and dissimilarity constraints between the descriptors. We show that our constraints nicely untangle the images from different objects and different views into clusters that are not only well-separated but also structured as the corresponding sets of poses: The Euclidean distance between descriptors is large when the descriptors are from different objects, and directly related to the distance between the poses when the descriptors are from the same object. These important properties allow us to outperform state-of-the-art object views representations on challenging RGB and RGB-D data.