HybridPose: 6D Object Pose Estimation under Hybrid Representations
This addresses pose estimation for robotics and AR/VR applications, offering an incremental improvement by combining existing representation types.
The paper tackles 6D object pose estimation by introducing HybridPose, which uses a hybrid representation of keypoints, edge vectors, and symmetry correspondences to improve robustness under occlusion, achieving a state-of-the-art mean ADD(-S) accuracy of 47.5% at 30 fps on the Occlusion Linemod dataset.
We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). Different intermediate representations used by HybridPose can all be predicted by the same simple neural network, and outliers in predicted intermediate representations are filtered by a robust regression module. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and accuracy. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 47.5%, representing a state-of-the-art performance. The implementation of HybridPose is available at https://github.com/chensong1995/HybridPose.