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

Wenjie Li*, Wasif Naeem, Jia Liu, Dequan Zheng, wei hao, Lijun Chen

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review


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 R^n 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 R^n 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.
Original languageEnglish
Number of pages10
Publication statusAccepted - 16 May 2022
EventThe 38th Conference on Uncertainty in Artificial Intelligence (UAI) - Eindhoven, Netherlands
Duration: 01 Aug 202205 Aug 2022


ConferenceThe 38th Conference on Uncertainty in Artificial Intelligence (UAI)
Abbreviated titleUAI2022
Internet address


Dive into the research topics of 'PDQ-Net: Deep Probabilistic Dual Quaternion Network for Absolute Pose Regression on SE(3)'. Together they form a unique fingerprint.

Cite this