Wide-Depth-Range 6D Object Pose Estimation in Space

TL;DR

This paper introduces a hierarchical end-to-end network for 6D object pose estimation in space, effectively handling large scale variations and outperforming existing methods on space-like and standard benchmarks.

Contribution

A novel single-stage hierarchical network that improves robustness to scale variations in space-based 6D pose estimation.

Findings

Outperforms existing methods on space-simulated images

Effective on standard benchmarks

Robust to large scale variations

Abstract

6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting. One of the most striking differences is the lack of atmospheric scattering, allowing objects to be visible from a great distance while complicating illumination conditions. Currently available benchmark datasets do not place a sufficient emphasis on this aspect and mostly depict the target in close proximity. Prior work tackling pose estimation under large scale variations relies on a two-stage approach to first estimate scale, followed by pose estimation on a resized image patch. We instead propose a single-stage hierarchical end-to-end trainable network that is more robust to scale variations. We demonstrate that it outperforms existing approaches not only on images synthesized to resemble images taken in space but also on standard benchmarks.