Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Prediction
This work addresses pose estimation for robotics or AR/VR applications, offering incremental improvements in handling occlusion.
The paper tackles the problem of 6D object pose estimation by proposing a bidirectional correspondence prediction network with point-wise attention, which improves robustness to occlusion. Experimental results on LineMOD, YCB-Video, and Occ-LineMOD datasets show it outperforms state-of-the-art methods under the same criteria.
Traditional geometric registration based estimation methods only exploit the CAD model implicitly, which leads to their dependence on observation quality and deficiency to occlusion. To address the problem,the paper proposes a bidirectional correspondence prediction network with a point-wise attention-aware mechanism. This network not only requires the model points to predict the correspondence but also explicitly models the geometric similarities between observations and the model prior. Our key insight is that the correlations between each model point and scene point provide essential information for learning point-pair matches. To further tackle the correlation noises brought by feature distribution divergence, we design a simple but effective pseudo-siamese network to improve feature homogeneity. Experimental results on the public datasets of LineMOD, YCB-Video, and Occ-LineMOD show that the proposed method achieves better performance than other state-of-the-art methods under the same evaluation criteria. Its robustness in estimating poses is greatly improved, especially in an environment with severe occlusions.