# Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models

arXiv: https://arxiv.org/abs/2509.05776 · HTML: https://mlsanity.com/paper/2509.05776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 69 references that are in the map.
- First posted on arXiv 6 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [3D Morphable Face Models -- Past, Present and Future](https://mlsanity.com/paper/1909.01815/) (2019)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Morphable Face Models - An Open Framework](https://mlsanity.com/paper/1709.08398/) (2017)
- [Validating Bayesian Inference Algorithms with Simulation-Based Calibration](https://mlsanity.com/paper/1804.06788/) (2018)
- [i3DMM: Deep Implicit 3D Morphable Model of Human Heads](https://mlsanity.com/paper/2011.14143/) (2020)
- [Unsupervised Training for 3D Morphable Model Regression](https://mlsanity.com/paper/1806.06098/) (2018)
- [Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow](https://mlsanity.com/paper/2203.08652/) (2022)
- [Gaussian Process Morphable Models](https://mlsanity.com/paper/1603.07254/) (2016)
- [High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey](https://mlsanity.com/paper/2011.08018/) (2020)
- [Invertible DenseNets with Concatenated LipSwish](https://mlsanity.com/paper/2102.02694/) (2021)
- [A survey on shape-constraint deep learning for medical image segmentation](https://mlsanity.com/paper/2101.07721/) (2021)
- [A Closest Point Proposal for MCMC-based Probabilistic Surface Registration](https://mlsanity.com/paper/1907.01414/) (2019)
- [Shape-aware Surface Reconstruction from Sparse 3D Point-Clouds](https://mlsanity.com/paper/1602.08425/) (2016)
- [Diffeomorphic Medial Modeling](https://mlsanity.com/paper/1902.02371/) (2019)

## Abstract (arXiv)

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.