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

Autor:	Guan, Qi, Sheng, Zihao, Xue, Shibei
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Computer Science - Robotics
Druh dokumentu:	Working Paper
DOI:	10.1049/cje.2021.00.211
Popis:	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. Comment: 8 pages, 4 figures, and 5 tables, accepted by Chinese Journal of Electronics
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2204.09429 Zobrazit plný text záznamu View this record from Arxiv