HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation

TL;DR

HRPose is a lightweight, real-time 6D object pose estimation network that uses knowledge distillation to improve accuracy while significantly reducing model size and computational costs, suitable for applications like robotics and AR.

Contribution

The paper introduces HRPose, a compact and efficient 6D pose estimation model that leverages knowledge distillation from larger models to enhance performance.

Findings

Achieves comparable accuracy with 33% of the model size of state-of-the-art methods.

Reduces computational costs while maintaining high performance.

Outperforms existing methods on the LINEMOD benchmark.

Abstract

Real-time 6D object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and lightweight model, namely High-Resolution 6D Pose Estimation Network (HRPose). We adopt the efficient and small HRNetV2-W18 as a feature extractor to reduce computational burdens while generating accurate 6D poses. With only 33\% of the model size and lower computational costs, our HRPose achieves comparable performance compared with state-of-the-art models. Moreover, by transferring knowledge from a large model to our proposed HRPose through output and feature-similarity distillations, the performance of our HRPose is improved in effectiveness and efficiency. Numerical experiments on the widely-used benchmark LINEMOD demonstrate the superiority of our proposed HRPose against state-of-the-art methods.