Object 6D Pose Estimation with Non-local Attention

TL;DR

This paper presents a deep learning approach for 6D object pose estimation from a single RGB image, integrating pose estimation into detection and enhancing robustness with a non-local attention module, achieving state-of-the-art results.

Contribution

It introduces a novel network that combines 6D pose estimation with object detection and incorporates a non-local self-attention module for occlusion robustness.

Findings

Achieves state-of-the-art performance on YCB-video dataset.

Demonstrates robustness to occlusion with the non-local attention module.

Efficient integration of pose estimation into detection framework.

Abstract

In this paper, we address the challenging task of estimating 6D object pose from a single RGB image. Motivated by the deep learning based object detection methods, we propose a concise and efficient network that integrate 6D object pose parameter estimation into the object detection framework. Furthermore, for more robust estimation to occlusion, a non-local self-attention module is introduced. The experimental results show that the proposed method reaches the state-of-the-art performance on the YCB-video and the Linemod datasets.