Special Unitary Parameterized Estimators of Rotation
For researchers in rotation estimation and neural network learning, this work provides new theoretical insights and practical representations, though it is incremental in nature.
The paper reformulates Wahba's problem using SU(2) matrices to derive linear constraints on quaternion parameters, leading to two novel continuous rotation representations for neural networks, validated by extensive experiments.
This paper revisits the topic of rotation estimation through the lens of special unitary matrices. We begin by reformulating Wahba's problem using $SU(2)$ to derive multiple solutions that yield linear constraints on corresponding quaternion parameters. We then explore applications of these constraints by formulating efficient methods for related problems. Finally, from this theoretical foundation, we propose two novel continuous representations for learning rotations in neural networks. Extensive experiments validate the effectiveness of the proposed methods.