HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation
This work addresses the need for efficient pose estimation in applications like robotic grasping and augmented reality, but it is incremental as it builds on existing methods with optimizations.
The paper tackles real-time 6D object pose estimation from RGB images by proposing HRPose, a lightweight model that uses HRNetV2-W18 and knowledge distillation, achieving comparable performance to state-of-the-art models with only 33% of the model size and lower computational costs.
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.