PDQ-Net: Deep Probabilistic Dual Quaternion Network for Absolute Pose Regression on SE(3)

Accurate absolute pose regression is one of the key challenges in robotics and computer vision. Existing direct regression methods suffer from two limitations. First, some noisy scenarios such as poor illumination conditions are likely to result in the uncertainty of pose estimation. Second, the output n-dimensional feature vector in the Euclidean space Rⁿ cannot be well mapped to SE(3) manifold. In this work, we propose a deep dual quaternion network that performs the absolute pose regression on SE(3). We first develop an antipodally symmetric probability distribution over the unit dual quaternion on SE(3) to model uncertainties and then propose an intermediary differential representation space to replace the final output pose, which avoids the mapping problem from Rⁿ to SE(3). In addition, we introduce a backpropagation method that considers the continuousness and differentiability of the proposed intermediary space. Extensive experiments on the camera re-localization task on the Cambridge Landmarks and 7-Scenes datasets demonstrate that our method greatly improves the accuracy of the pose as well as the robustness in dealing with uncertainty and ambiguity, compared to the state-of-the-art.