Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.05776 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916937680814080 |
|---|---|
| author | Aellen, Jonathan Burkhardt, Florian Vetter, Thomas Lüthi, Marcel |
| author_facet | Aellen, Jonathan Burkhardt, Florian Vetter, Thomas Lüthi, Marcel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05776 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models Aellen, Jonathan Burkhardt, Florian Vetter, Thomas Lüthi, Marcel Computer Vision and Pattern Recognition 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. |
| title | Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.05776 |