Pose Estimation using Local Structure-Specific Shape and Appearance Context

TL;DR

This paper introduces a novel local descriptor combining 2D image and 3D shape data for improved pose estimation between models, demonstrating high discriminative power and effectiveness in various scenarios.

Contribution

It presents a new structure-specific local descriptor that integrates appearance and shape information for pose estimation, outperforming existing methods.

Findings

Descriptors show higher discriminative power than state-of-the-art approaches.

Effective in controlled and real-life pose estimation scenarios.

Improves alignment accuracy between 3D models.

Abstract

We address the problem of estimating the alignment pose between two models using structure-specific local descriptors. Our descriptors are generated using a combination of 2D image data and 3D contextual shape data, resulting in a set of semi-local descriptors containing rich appearance and shape information for both edge and texture structures. This is achieved by defining feature space relations which describe the neighborhood of a descriptor. By quantitative evaluations, we show that our descriptors provide high discriminative power compared to state of the art approaches. In addition, we show how to utilize this for the estimation of the alignment pose between two point sets. We present experiments both in controlled and real-life scenarios to validate our approach.