Object 6D Pose Estimation with Non-local Attention
This addresses pose estimation for robotics and AR/VR applications, but it is incremental as it builds on existing detection methods with a novel attention module.
The paper tackled 6D object pose estimation from a single RGB image by integrating pose estimation into an object detection framework and adding a non-local self-attention module for occlusion robustness, achieving state-of-the-art performance on YCB-video and Linemod datasets.
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.