In medical imaging, point distribution models are often used to reconstruct and complete partial shapes using a statistical model of the full shape. A commonly overlooked, but crucial factor in this reconstruction process, is the pose of the training data relative to the partial target shape. A difference in pose alignment of the training and target shape leads to biased solutions, particularly when observing small parts of a shape. In this paper, we demonstrate the importance of pose alignment for partial shape reconstructions and propose an efficient method to adjust an existing model to a specific target. Our method preserves the computational efficiency of linear models while significantly improving reconstruction accuracy and predicted variance. It exactly recovers the intended aligned model for translations, and provides a good approximation for small rotations, all without access to the original training data. Hence, existing shape models in reconstruction pipelines can be adapted by a simple preprocessing step, making our approach widely applicable in plug-and-play scenarios.
View on arXiv