Posterior shape models

Albrecht, Thomas; Lüthi, Marcel; Gerig, Thomas M.; Vetter, Thomas

doi:10.1016/j.media.2013.05.010

Cited by 67 publications

(50 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main issues with the SSM approach is that the search for robust point correspondences on different shapes is complex and can be prone to outliers, potentially impairing the quality of the mean model, the PCA decomposition, and compromising the extrapolation property of the model . For instance, the simple minimum distance criterion depends on the surface local sampling and can easily lead to multiple‐to‐one matches.…”

Section: Discussionmentioning

confidence: 99%

“…The advantage of PCA‐based reconstruction is that the sorted eigenmodes account for decreasing levels of shape dissimilarities thus granting that the contribution of one eigenvector becomes more and more negligible as the corresponding eigenvalue approaches zero. Mathematically, this can be quantified by using the concept of explained variance (EV), which correlates each eigenvalue to a specific percentage of variation into the surface set, so that summing up all the eigenmodes equals 100% . By enduring a reduction of the reconstruction quality, while acceptable, it is possible to represent the morphing synthetically using only H variation modes ( H < M ), representing the most relevant contributions of the dataset dissimilarities.…”

Section: Materials and Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Stacked sparse autoencoder networks and statistical shape models for automatic staging of distal femur trochlear dysplasia

Cerveri

Belfatto

Baroni

et al. 2018

Int J Med Robotics Comput Assist Surg

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Materials and Methodologymentioning

confidence: 99%

Stacked sparse autoencoder networks and statistical shape models for automatic staging of distal femur trochlear dysplasia

Cerveri

Belfatto

Baroni

et al. 2018

Int J Med Robotics Comput Assist Surg

View full text Add to dashboard Cite

show abstract

“…For the prediction, a Gaussian process regression method was applied, as described in . The main idea is that given the healthy surface regions of the radius and ulna (Fig.…”

Section: Methodsmentioning

confidence: 99%

Prediction of normal bone anatomy for the planning of corrective osteotomies of malunited forearm bones using a three‐dimensional statistical shape model

Mauler

Langguth

Schweizer

et al. 2017

Journal Orthopaedic Research

Self Cite

View full text Add to dashboard Cite

Corrective osteotomies of the forearm based on 3D computer simulation using contralateral anatomy as a reconstruction template is an approved method. Limitations are existing considerable differences between left and right forearms, and that a healthy contralateral anatomy is required. We evaluated if a computer model, not relying on the contralateral anatomy, may replace the current method by predicting the pre-traumatic healthy shape. A statistical shape model (SSM) was generated from a set of 59 CT scans of healthy forearms, encoding the normal anatomical variations. Three different configurations were simulated to predict the pre-traumatic shape with the SSM (cross-validation). In the first two, only the distal or proximal 50% of the radius were considered as pathological. In a third configuration, the entire radius was assumed to be pathological, only the ulna being intact. Corresponding experiments were performed with the ulna. Accuracy of the prediction was assessed by comparing the predicted bone with the healthy model. For the radius, mean rotation accuracy of the prediction between 2.9 ± 2.2° and 4.0 ± 3.1° in pronation/supination, 0.4 ± 0.3° and 0.6 ± 0.5° in flexion/extension, between 0.5 ± 0.3° and 0.5 ± 0.4° in radial-/ulnarduction. Mean translation accuracy along the same axes between 0.8 ± 0.7 and 1.0 ± 0.8 mm, 0.5 ± 0.4 and 0.6 ± 0.4 mm, 0.6 ± 0.4 and 0.6 ± 0.5 mm, respectively. For the ulna, mean rotation accuracy between 2.4 ± 1.9° and 4.7 ± 3.8° in pronation/supination, 0.3 ± 0.3° and 0.8 ± 0.6° in flexion/extension, 0.3 ± 0.2° and 0.7 ± 0.6° in radial-/ulnarduction. Mean translation accuracy between 0.6 ± 0.4 mm and 1.3 ± 0.9 mm, 0.4 ± 0.4 mm and 0.7 ± 0.5 mm, 0.5 ± 0.4 mm and 0.8 ± 0.6 mm, respectively. This technique provided high accuracy, and may replace the current method, if validated in clinical studies. © 2017 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 35:2630-2636, 2017.

show abstract

“…in Cootes et al (2001) and Blanz and Vetter (1999). To get a real prior distribution on the complete data space, a probabilistic extension through Probabilistic PCA (PPCA) is necessary (Tipping and Bishop 1999;Albrecht et al 2013), see Sect. 3.1.…”

Section: Parametric Appearance Modelsmentioning

confidence: 99%

“…Such a model is also defined outside the linear span of the training samples and can thus be directly used as a prior distribution of face shape and appearance. This is achieved by adding a spherical Gaussian noise term in the sample space (Albrecht et al 2013;Tipping and Bishop 1999). Our model then becomes…”

Section: Face Modelmentioning

confidence: 99%

Markov Chain Monte Carlo for Automated Face Image Analysis

et al. 2016

Self Cite

View full text Add to dashboard Cite

We present a novel fully probabilistic method to interpret a single face image with the 3D Morphable Model. The new method is based on Bayesian inference and makes use of unreliable image-based information. Rather than searching a single optimal solution, we infer the posterior distribution of the model parameters given the target image. The method is a stochastic sampling algorithm with a propose-and-verify architecture based on the MetropolisHastings algorithm. The stochastic method can robustly integrate unreliable information and therefore does not rely on feed-forward initialization. The integrative concept is based on two ideas, a separation of proposal moves and their verification with the model (Data-Driven Markov Chain Monte Carlo), and filtering with the Metropolis acceptance rule. It does not need gradients and is less prone to local optima than standard fitters. We also introduce a new collective likelihood which models the average difference between the model and the target image rather than individual pixel differences. The average value shows a natural tendency towards a normal distribution, even when the individual pixel-wise difference is not Gaussian. We employ the new fitting method to calculate posterior models of 3D face reconstructions from single real-world images. A direct application of the algorithm with the 3D Morphable Model leads us to a fully automatic face recognition system with competitive performance on the Multi-PIE database without any database adaptation.

show abstract

Posterior shape models

Cited by 67 publications

References 24 publications

Stacked sparse autoencoder networks and statistical shape models for automatic staging of distal femur trochlear dysplasia

Stacked sparse autoencoder networks and statistical shape models for automatic staging of distal femur trochlear dysplasia

Prediction of normal bone anatomy for the planning of corrective osteotomies of malunited forearm bones using a three‐dimensional statistical shape model

Markov Chain Monte Carlo for Automated Face Image Analysis

Contact Info

Product

Resources

About